© 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. 91702
    Prev
    Next
    INDEX
    Explanations

    scientific comparisons and classifications related to biological characteristics

    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
     circumstances
    -0.06
    affles
    -0.06
    877
    -0.06
    vos
    -0.06
    ENÃį
    -0.06
    opl
    -0.06
    PropertyDescriptor
    -0.06
    stdarg
    -0.06
    iris
    -0.06
     trÃŃ
    -0.06
    POSITIVE LOGITS
    éģĵ
    0.06
    ãĥĥãĤ«ãĥ¼
    0.06
    .getOwnProperty
    0.06
    innitus
    0.06
     values
    0.06
    unner
    0.06
    ÅĽcie
    0.06
    _share
    0.06
    aday
    0.06
    rowned
    0.06
    Activations Density 0.003%

    No Known Activations