© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 81326
    Prev
    Next
    INDEX
    Explanations

    code-related comments and directives

    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
    pong
    -0.06
    kees
    -0.06
    erge
    -0.06
     fig
    -0.06
     Sink
    -0.06
    792
    -0.06
    cke
    -0.06
    estre
    -0.06
     Kick
    -0.06
     craw
    -0.06
    POSITIVE LOGITS
    Wunused
    0.07
    cop
    0.07
    MBProgressHUD
    0.07
    )||(
    0.07
     cup
    0.06
    _UTF
    0.06
    ucursal
    0.06
     acomp
    0.06
    .snapshot
    0.06
    cup
    0.06
    Activations Density 0.001%

    No Known Activations