© 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. 69971
    Prev
    Next
    INDEX
    Explanations

    commands related to output and logging 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
    odie
    -0.07
    pen
    -0.07
    /inet
    -0.07
    .zero
    -0.07
    /apt
    -0.07
    ÙĪØŃ
    -0.07
     usted
    -0.07
    vero
    -0.07
    ê»
    -0.07
    yo
    -0.07
    POSITIVE LOGITS
     CASCADE
    0.07
     Byl
    0.05
    edb
    0.05
    .NewLine
    0.05
    æĽ°
    0.05
    apons
    0.05
    _stderr
    0.05
    memberOf
    0.05
    733
    0.05
    sizeof
    0.05
    Activations Density 0.008%

    No Known Activations