© 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. 28886
    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
    èo
    -0.07
    .MixedReality
    -0.07
     hra
    -0.07
    práv
    -0.07
    ettle
    -0.07
    ÃŃrk
    -0.07
    Ìģc
    -0.07
    imbus
    -0.07
    isd
    -0.07
    зÑĭ
    -0.07
    POSITIVE LOGITS
    Ĥ
    0.07
     migrationBuilder
    0.06
    stown
    0.06
    ussed
    0.06
    /repos
    0.06
     from
    0.06
     scales
    0.06
    /src
    0.06
    -ie
    0.05
    BA
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.