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. 9-LLAMASCOPE-RES-131K
    6. 96114
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    .vn
    -0.07
    ingham
    -0.07
    ML
    -0.06
     Thur
    -0.06
    adora
    -0.06
    tam
    -0.06
    GIT
    -0.06
    .tk
    -0.06
    ocab
    -0.06
    iselect
    -0.06
    POSITIVE LOGITS
    Ñıн
    0.07
     casts
    0.07
     CAST
    0.07
    Cast
    0.07
    ycle
    0.06
     Cast
    0.06
     Platt
    0.06
    CAST
    0.06
    dae
    0.06
    _STYLE
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.