© 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. 106452
    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
    --[[
    -0.07
    .hxx
    -0.07
    ityEngine
    -0.07
    oup
    -0.07
     addCriterion
    -0.07
    ноÑģ
    -0.07
    .unknown
    -0.07
    linger
    -0.07
    lds
    -0.07
    .throw
    -0.07
    POSITIVE LOGITS
    arga
    0.06
     Prem
    0.06
     Simone
    0.06
    ault
    0.06
    bin
    0.06
     ker
    0.06
    ,
    0.06
     women
    0.06
     religion
    0.05
     superst
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.