© 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. 9-LLAMASCOPE-RES-131K
    11. 94204
    Prev
    Next
    INDEX
    Explanations

    instances of the word "right" and its variations

    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
    umar
    -0.08
    ague
    -0.06
    arend
    -0.06
    é¤
    -0.06
     jar
    -0.06
    redit
    -0.06
    iston
    -0.06
    agua
    -0.06
    wap
    -0.06
    qv
    -0.06
    POSITIVE LOGITS
    tributes
    0.06
    assel
    0.06
    auses
    0.06
     Äiju
    0.06
    atte
    0.06
    _sdk
    0.06
    InRange
    0.06
     pii
    0.06
    anje
    0.06
    poz
    0.06
    Activations Density 0.003%

    No Known Activations