© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 89871
    Prev
    Next
    INDEX
    Explanations

    connections and patterns in data analysis

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    Ñģлов
    -0.08
    imbus
    -0.07
    è©
    -0.07
    chner
    -0.07
    .Parcelable
    -0.07
    iazza
    -0.07
    elsing
    -0.07
    &B
    -0.06
    boo
    -0.06
    assa
    -0.06
    POSITIVE LOGITS
     evidence
    0.13
     indication
    0.10
     indicates
    0.09
     facts
    0.09
     indicating
    0.08
     Evidence
    0.08
     evid
    0.08
     indicate
    0.08
     argue
    0.08
     argument
    0.08
    Activations Density 0.143%

    No Known Activations