© 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. 14352
    Prev
    Next
    INDEX
    Explanations

    instances of the word "decide" 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
    orp
    -0.07
    usat
    -0.07
    cards
    -0.07
    æĮģ
    -0.06
    uggestions
    -0.06
    rej
    -0.06
     Vác
    -0.06
    oret
    -0.06
    stants
    -0.06
    aná
    -0.06
    POSITIVE LOGITS
     rằng
    0.09
    icode
    0.07
     to
    0.07
    784
    0.07
     that
    0.07
    aida
    0.07
    ANGED
    0.07
     bahwa
    0.06
    483
    0.06
     pursue
    0.06
    Activations Density 0.009%

    No Known Activations