© 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 EvalsExportsAPI 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. 86031
    Prev
    Next
    INDEX
    Explanations

    elements or variables related to coding or programming syntax

    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
    auss
    -0.08
    yk
    -0.08
    -aos
    -0.07
     strav
    -0.07
    ër
    -0.07
    æ³Ĭ
    -0.07
    ngine
    -0.07
    iless
    -0.07
    usement
    -0.07
    OLON
    -0.07
    POSITIVE LOGITS
     gates
    0.06
     Kraj
    0.06
     Kob
    0.06
     tall
    0.06
    radu
    0.06
     Gib
    0.05
     Dawn
    0.05
    _cv
    0.05
    .↵↵↵↵↵↵↵↵
    0.05
     harm
    0.05
    Activations Density 0.000%

    No Known Activations