© 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. 77317
    Prev
    Next
    INDEX
    Explanations

    specific punctuation and formatting used in code or programming contexts

    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
    izzo
    -0.08
    vic
    -0.07
    reau
    -0.07
    borg
    -0.07
    gis
    -0.07
    ovsky
    -0.07
    izio
    -0.06
    ekil
    -0.06
     ciz
    -0.06
    ream
    -0.06
    POSITIVE LOGITS
    rief
    0.07
    ả
    0.06
     overall
    0.06
    /=
    0.06
    ayer
    0.06
    _FLUSH
    0.06
    flation
    0.06
    Pretty
    0.06
    atha
    0.06
     Pretty
    0.06
    Activations Density 0.006%

    No Known Activations