© 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. 14246
    Prev
    Next
    INDEX
    Explanations

    commands and functions related to coding and directory management

    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
    ules
    -0.08
    ãĤ¦ãĥĪ
    -0.07
     Stein
    -0.06
    .btnCancel
    -0.06
    ucer
    -0.06
    esco
    -0.06
    ackle
    -0.06
    indow
    -0.06
    feito
    -0.06
    981
    -0.06
    POSITIVE LOGITS
    .exe
    0.07
     Karlov
    0.07
     Gust
    0.07
    Jam
    0.07
    _tac
    0.07
    稿
    0.07
     -
    0.06
    ectl
    0.06
    icontrol
    0.06
    igidBody
    0.06
    Activations Density 0.012%

    No Known Activations