© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 29303
    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
     outstanding
    -0.06
    ãģĭãģ«
    -0.06
     Shorts
    -0.06
    ¦Ĥ
    -0.06
     ‘
    -0.06
    sdale
    -0.05
    .pages
    -0.05
    CCC
    -0.05
    ünd
    -0.05
    &E
    -0.05
    POSITIVE LOGITS
    ecz
    0.08
    iek
    0.07
    اض
    0.07
    eton
    0.07
    okoj
    0.07
     fucking
    0.07
    artisan
    0.06
    loquent
    0.06
    edy
    0.06
    emoc
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.