© 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. 129002
    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
    ams
    -0.06
     Dow
    -0.06
     pret
    -0.06
    okin
    -0.06
     NAS
    -0.06
     pac
    -0.06
     pur
    -0.06
    ither
    -0.06
    hood
    -0.06
     pro
    -0.05
    POSITIVE LOGITS
    mont
    0.08
    stanov
    0.08
    loo
    0.07
    byn
    0.07
    ogo
    0.07
    ritz
    0.07
    رÙĪب
    0.07
    ayo
    0.07
    come
    0.06
    illos
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.