© 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. 6009
    Prev
    Next
    INDEX
    Explanations

    instances of the word "wrote" and its conjugations

    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
    chant
    -0.07
     tac
    -0.06
    983
    -0.06
    ãĥ¼ãĥĬ
    -0.06
    aman
    -0.06
    944
    -0.06
    hdl
    -0.06
    wang
    -0.06
     Nelson
    -0.06
    дем
    -0.06
    POSITIVE LOGITS
    ecut
    0.08
    -chevron
    0.08
    udoku
    0.07
    /is
    0.07
    ÅĻÃŃm
    0.07
    ModelAttribute
    0.07
    -toggler
    0.07
    onse
    0.07
    alers
    0.07
    oldem
    0.07
    Activations Density 0.002%

    No Known Activations