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. 8-LLAMASCOPE-RES-32K
    6. 6508
    Prev
    Next
    INDEX
    Explanations

    expressions related to the condemnation of sexual assault and violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 8-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     á
    -0.17
    çŃĭ
    -0.15
    ovable
    -0.14
     vend
    -0.14
     trades
    -0.14
     bl
    -0.14
    amps
    -0.13
     ta
    -0.13
    ao
    -0.13
    iad
    -0.13
    POSITIVE LOGITS
    ippo
    0.17
    /command
    0.16
    mise
    0.16
    ument
    0.16
    edla
    0.15
     Arap
    0.15
    band
    0.15
    yon
    0.14
    жен
    0.14
    eric
    0.14
    Activations Density 0.323%

    No Known Activations