© 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. 80579
    Prev
    Next
    INDEX
    Explanations

    mentions of drafts and signings in sports contexts

    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
    bane
    -0.07
    _HOR
    -0.06
     mort
    -0.06
    _ser
    -0.06
     Vance
    -0.06
    icc
    -0.06
    yal
    -0.06
    ayas
    -0.06
    apus
    -0.06
    anki
    -0.06
    POSITIVE LOGITS
    Signing
    0.07
    _finalize
    0.07
     bonus
    0.07
     Signing
    0.07
     pec
    0.06
     Closed
    0.06
     Bonus
    0.06
    ól
    0.06
    dee
    0.06
     Klo
    0.06
    Activations Density 0.008%

    No Known Activations