© 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. 98310
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and control flow structures

    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
    edik
    -0.06
    .bz
    -0.06
    ucken
    -0.06
    _dot
    -0.06
    lete
    -0.06
    обов
    -0.06
    itz
    -0.06
     BITS
    -0.06
    haar
    -0.05
     Near
    -0.05
    POSITIVE LOGITS
    iju
    0.07
    Ïĥμο
    0.07
    InBackground
    0.07
     -*-č↵
    0.07
    afen
    0.07
    -INF
    0.06
    /GPL
    0.06
    anon
    0.06
    allery
    0.06
    ündeki
    0.06
    Activations Density 0.000%

    No Known Activations