© 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. 90149
    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
    hang
    -0.07
    Ľi
    -0.07
    kol
    -0.06
    CLUDED
    -0.06
    ectomy
    -0.06
    aho
    -0.06
    au
    -0.06
    kar
    -0.06
    haust
    -0.06
    enco
    -0.06
    POSITIVE LOGITS
     Consent
    0.07
    åĤ
    0.07
    ighthouse
    0.06
    ,strlen
    0.06
     palp
    0.06
    igu
    0.06
    _YUV
    0.06
    Ñģок
    0.06
    FTA
    0.06
     NONINFRINGEMENT
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.