© 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. 9-LLAMASCOPE-RES-131K
    11. 97721
    Prev
    Next
    INDEX
    Explanations

    function calls and method execution within a programming context

    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
    hood
    -0.09
    or
    -0.06
    689
    -0.06
     legisl
    -0.06
    re
    -0.05
     tension
    -0.05
     Masc
    -0.05
    RAIN
    -0.05
     Nash
    -0.05
     Dunn
    -0.05
    POSITIVE LOGITS
    帯
    0.08
    uai
    0.08
    emey
    0.08
    eworld
    0.07
    jar
    0.07
    ải
    0.07
    ramework
    0.07
    çĽijåIJ¬é¡µéĿ¢
    0.07
    croft
    0.07
    oppel
    0.07
    Activations Density 0.028%

    No Known Activations