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. 3-LLAMASCOPE-RES-32K
    6. 3413
    Prev
    Next
    INDEX
    Explanations

    elements related to user engagement and user-friendly design

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    toy
    -0.15
    quences
    -0.15
    oker
    -0.14
    Fld
    -0.14
    Extern
    -0.14
    سÙĪÙĨ
    -0.14
    .spec
    -0.14
    ectors
    -0.14
    ownt
    -0.13
     Sag
    -0.13
    POSITIVE LOGITS
    ause
    0.15
    ibble
    0.15
     hence
    0.15
    atz
    0.14
    缼
    0.14
     Hib
    0.14
    ught
    0.14
     lingu
    0.14
    icom
    0.14
    ikh
    0.13
    Activations Density 0.082%

    No Known Activations