© 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. 69036
    Prev
    Next
    INDEX
    Explanations

    interactions and responses in discussions

    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
    usan
    -0.06
    iri
    -0.06
    ings
    -0.06
    bold
    -0.06
    ereg
    -0.06
     Goldberg
    -0.06
    eder
    -0.06
    Identity
    -0.06
    Bold
    -0.06
    aul
    -0.06
    POSITIVE LOGITS
    ë£Į
    0.07
    upert
    0.07
    hift
    0.07
    pq
    0.07
     Nurs
    0.07
    .transitions
    0.07
    ãĥ³ãĥĨ
    0.07
    าระ
    0.06
    ArrayOf
    0.06
    ameda
    0.06
    Activations Density 0.001%

    No Known Activations