© 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. 95907
    Prev
    Next
    INDEX
    Explanations

    code-related syntax and keywords

    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
    825
    -0.06
    drs
    -0.06
    meld
    -0.06
    enaries
    -0.06
    824
    -0.06
    abajo
    -0.06
     Sug
    -0.06
    190
    -0.05
    rote
    -0.05
    оваÑĢ
    -0.05
    POSITIVE LOGITS
     cryst
    0.07
    aya
    0.07
     Swinger
    0.07
     queryInterface
    0.07
     Karn
    0.06
    ubu
    0.06
    &type
    0.06
     LOC
    0.06
    .datab
    0.06
    _a
    0.06
    Activations Density 0.001%

    No Known Activations