© 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. 1502
    Prev
    Next
    INDEX
    Explanations

    expressions of will or intention

    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
    elli
    -0.08
    ils
    -0.07
     onKeyDown
    -0.07
     WithEvents
    -0.07
    ASY
    -0.06
     Sund
    -0.06
     Goat
    -0.06
    esis
    -0.06
    egov
    -0.06
    vig
    -0.06
    POSITIVE LOGITS
    power
    0.10
    idata
    0.08
    ough
    0.07
    awai
    0.07
    ful
    0.07
    iger
    0.07
    bservice
    0.07
    idd
    0.07
    ocos
    0.06
     power
    0.06
    Activations Density 0.008%

    No Known Activations