© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 93565
    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
     Cummings
    -0.07
    agan
    -0.06
    actual
    -0.06
    agas
    -0.06
     Rex
    -0.06
     either
    -0.06
     usted
    -0.06
    and
    -0.05
    /print
    -0.05
     im
    -0.05
    POSITIVE LOGITS
    .Alter
    0.08
    .AddField
    0.07
    tuk
    0.07
    ptal
    0.07
    sou
    0.07
    éĥij
    0.07
     Harr
    0.07
    kker
    0.07
    ç¼
    0.06
    TES
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.