© 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. 123439
    Prev
    Next
    INDEX
    Explanations

    instances of the word "to" in relation to actions or movements

    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
     Basket
    -0.07
    loff
    -0.07
    enties
    -0.07
    yc
    -0.07
    oun
    -0.07
    ãĥ³ãĥij
    -0.06
    $__
    -0.06
    lant
    -0.06
    /Runtime
    -0.06
    ych
    -0.06
    POSITIVE LOGITS
     basics
    0.07
     Sender
    0.07
    asser
    0.07
     sender
    0.07
     fray
    0.07
     haunt
    0.06
     fold
    0.06
     prominence
    0.06
     earth
    0.06
    atch
    0.06
    Activations Density 0.017%

    No Known Activations