© 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. 18674
    Prev
    Next
    INDEX
    Explanations

    keywords related to module exports in programming

    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
    heim
    -0.07
    ingen
    -0.07
    afa
    -0.06
    Æ¡i
    -0.06
    ixin
    -0.06
    orm
    -0.06
    ela
    -0.06
    ipment
    -0.06
    ãĥ¼ãĥĢ
    -0.06
    etic
    -0.06
    POSITIVE LOGITS
    azer
    0.08
    lant
    0.07
    isor
    0.07
     VÄĽ
    0.06
    undry
    0.06
     Punch
    0.06
    à¤¾à¤Ł
    0.06
    edn
    0.06
    discard
    0.06
    addir
    0.06
    Activations Density 0.002%

    No Known Activations