© 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. 104111
    Prev
    Next
    INDEX
    Explanations

    variations of the name "Fenner" and related terms

    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
    gor
    -0.08
    idor
    -0.07
    IMITIVE
    -0.07
    irie
    -0.07
    portun
    -0.06
    igy
    -0.06
    .diag
    -0.06
    eson
    -0.06
    deen
    -0.06
    .dot
    -0.06
    POSITIVE LOGITS
    ucht
    0.07
    wick
    0.07
    cko
    0.07
    etration
    0.07
    426
    0.07
    435
    0.06
    ancial
    0.06
    491
    0.06
     Bilg
    0.06
    yal
    0.06
    Activations Density 0.021%

    No Known Activations