© 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. 95131
    Prev
    Next
    INDEX
    Explanations

    references to administrative processes and legal procedures

    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
    ré
    -0.07
    reh
    -0.07
    sap
    -0.07
     Tick
    -0.07
    pin
    -0.06
     sap
    -0.06
    apolis
    -0.06
    allo
    -0.06
     Unsupported
    -0.06
     Turnbull
    -0.06
    POSITIVE LOGITS
     mistake
    0.16
     error
    0.14
    éĶĻ误
    0.11
     mistakes
    0.11
     Mist
    0.11
    误
    0.11
    mist
    0.10
     typo
    0.10
    error
    0.10
    -error
    0.10
    Activations Density 0.050%

    No Known Activations