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

    Neuronpedia

    APICircuit 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. 31-LLAMASCOPE-RES-131K
    6. 43923
    Prev
    Next
    INDEX
    Explanations

    symbols and mathematical notations commonly used in scientific and technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     articles
    -0.06
    æķĻ
    -0.06
    .ValidationError
    -0.06
    åŀĭ
    -0.06
    ارÙģ
    -0.06
    è©
    -0.06
     Jaune
    -0.06
    articles
    -0.06
     BÃł
    -0.06
    ButtonType
    -0.06
    POSITIVE LOGITS
     caption
    0.15
     togg
    0.10
     Caption
    0.10
     toggle
    0.10
    -caption
    0.10
     captions
    0.09
    caption
    0.09
     hide
    0.09
    _caption
    0.09
    toggle
    0.09
    Activations Density 0.004%

    No Known Activations