© 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. 15-LLAMASCOPE-RES-131K
    11. 86042
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "In" when discussing events or details

    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
    ipples
    -0.07
    öh
    -0.07
    319
    -0.07
    ergency
    -0.06
    structor
    -0.06
    ög
    -0.06
    igmat
    -0.06
    olumn
    -0.06
    osis
    -0.06
    igma
    -0.06
    POSITIVE LOGITS
    lev
    0.06
    æ³³
    0.06
    ale
    0.06
    oby
    0.06
    LEV
    0.06
     nut
    0.06
    edata
    0.06
    ible
    0.06
    ames
    0.06
    elves
    0.06
    Activations Density 0.019%

    No Known Activations