© 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. 2563
    Prev
    Next
    INDEX
    Explanations

    structural or syntax-related elements in code snippets

    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
    DOT
    -0.07
    slaught
    -0.07
     metall
    -0.07
     Gros
    -0.07
    _DOT
    -0.07
    rier
    -0.06
    .setAction
    -0.06
    βά
    -0.06
    /board
    -0.06
    -lock
    -0.06
    POSITIVE LOGITS
     caught
    0.07
     failure
    0.07
    PLICIT
    0.07
     catch
    0.07
     failing
    0.06
     ìĭ¤í
    0.06
     Fail
    0.06
    ermen
    0.06
     sen
    0.06
     onFailure
    0.06
    Activations Density 0.011%

    No Known Activations