© 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. 121231
    Prev
    Next
    INDEX
    Explanations

    code elements related to methods and functions in programming

    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
    anik
    -0.07
    iosper
    -0.06
    alam
    -0.06
    867
    -0.06
    tract
    -0.06
    osto
    -0.06
    amu
    -0.06
    123
    -0.06
    fit
    -0.06
     avent
    -0.06
    POSITIVE LOGITS
    ULE
    0.07
    mers
    0.06
    ule
    0.06
    umb
    0.06
     guarante
    0.06
     UIG
    0.06
    ergus
    0.06
    à¥īà¤Ł
    0.06
    orde
    0.06
    ruh
    0.06
    Activations Density 0.026%

    No Known Activations