© 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. 121359
    Prev
    Next
    INDEX
    Explanations

    programming annotations and builders for object serialization

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ково
    -0.06
    kova
    -0.06
    olson
    -0.06
    332
    -0.06
    ains
    -0.06
    UrlParser
    -0.06
    fone
    -0.06
    yy
    -0.06
     Robbins
    -0.06
     Phaser
    -0.06
    POSITIVE LOGITS
    .build
    0.08
    build
    0.08
     build
    0.07
    .commit
    0.07
    ETCH
    0.07
     commit
    0.06
    asant
    0.06
    æŀľ
    0.06
    -commit
    0.06
    agus
    0.06
    Activations Density 0.010%

    No Known Activations