© 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 EvalsExportsinterp-engineNEWAPI 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. 92214
    Prev
    Next
    INDEX
    Explanations

    mentions of dates, historical events, and political figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Contr
    -0.07
    .Apis
    -0.07
    .gdx
    -0.07
    .snp
    -0.06
    quier
    -0.06
    aint
    -0.06
     Vegas
    -0.06
    \Persistence
    -0.06
    ertainment
    -0.06
     DeV
    -0.06
    POSITIVE LOGITS
    ÏĦοι
    0.07
    '=>"
    0.07
    "+"
    0.07
    ÙĤÙĬ
    0.07
    /vendors
    0.07
    siz
    0.07
    ÑĨен
    0.06
     dikke
    0.06
    niejs
    0.06
    -buttons
    0.06
    Activations Density 0.011%

    No Known Activations