© 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. 81641
    Prev
    Next
    INDEX
    Explanations

    references to surgical procedures and operations

    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
     pry
    -0.06
    encia
    -0.06
    ates
    -0.06
    ensi
    -0.06
    usta
    -0.06
     Pry
    -0.06
    ened
    -0.06
    anche
    -0.06
     unintention
    -0.06
    ná
    -0.06
    POSITIVE LOGITS
     performed
    0.10
    Performed
    0.09
    /testing
    0.08
     done
    0.08
     conducted
    0.08
    otron
    0.08
    chedulers
    0.08
    done
    0.08
    evice
    0.07
    platz
    0.07
    Activations Density 0.010%

    No Known Activations