© 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. 15-LLAMASCOPE-RES-131K
    11. 104082
    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
    enek
    -0.08
    [".
    -0.07
    utzer
    -0.07
     sop
    -0.07
    UTC
    -0.07
    ields
    -0.07
    .nano
    -0.07
    ield
    -0.07
    коп
    -0.07
    ẫ
    -0.06
    POSITIVE LOGITS
    igham
    0.08
    otor
    0.06
    fang
    0.06
    rend
    0.06
    OTOR
    0.06
     predis
    0.06
     honeymoon
    0.06
    tor
    0.06
     Fang
    0.06
    /welcome
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.