© 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. 1224
    Prev
    Next
    INDEX
    Explanations

    terms related to functionality and troubleshooting in coding 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
    jis
    -0.07
    priv
    -0.06
    onium
    -0.06
    amina
    -0.06
    enu
    -0.06
    ITT
    -0.06
    ìĽĶ
    -0.06
    ãĤĨ
    -0.06
     Ali
    -0.06
    aten
    -0.06
    POSITIVE LOGITS
    kaar
    0.07
     vo
    0.07
    ilha
    0.07
     problem
    0.07
     solution
    0.07
    cosa
    0.06
     Karlov
    0.06
    .problem
    0.06
    ailed
    0.06
    problem
    0.06
    Activations Density 0.017%

    No Known Activations