Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 14-LLAMASCOPE-RES-32K
    6. 28135
    Prev
    Next
    INDEX
    Explanations

    references to specific geographic locations or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Curtis
    -0.14
    anos
    -0.13
     Roose
    -0.13
    iola
    -0.13
    eton
    -0.13
     Mec
    -0.13
    uzey
    -0.13
    ylland
    -0.13
    lying
    -0.12
    exus
    -0.12
    POSITIVE LOGITS
    ldkf
    0.14
    fsp
    0.13
    uko
    0.13
    deen
    0.13
    onet
    0.13
    ocoder
    0.12
    ory
    0.12
    taÅŁ
    0.12
    ãĥ«ãĤ¯
    0.12
    á»ijng
    0.12
    Activations Density 1.304%

    No Known Activations