© 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. 63042
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "f" in various contexts

    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
    resco
    -0.07
    ynn
    -0.06
     fucking
    -0.06
    idges
    -0.06
    azzi
    -0.06
     redund
    -0.06
    endir
    -0.06
     fuck
    -0.06
    erer
    -0.06
    anner
    -0.06
    POSITIVE LOGITS
     frags
    0.07
    angered
    0.07
     Weinstein
    0.07
    ÑĤÑİ
    0.07
    ìĬ¤íģ¬
    0.07
    -lang
    0.06
    poon
    0.06
    _shutdown
    0.06
    uming
    0.06
    .react
    0.06
    Activations Density 0.000%

    No Known Activations