© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 78104
    Prev
    Next
    INDEX
    Explanations

    structured code blocks and syntax elements in programming language scripts

    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
    ört
    -0.07
    BREAK
    -0.06
    .struts
    -0.06
    ewater
    -0.06
    arin
    -0.06
    inky
    -0.06
     Silver
    -0.06
     Mul
    -0.06
    гоÑĢ
    -0.06
     Break
    -0.06
    POSITIVE LOGITS
    folio
    0.07
    uper
    0.07
    erable
    0.06
    ä¸ĬãģĮ
    0.06
    gage
    0.06
     Gauge
    0.06
    uzey
    0.06
    zen
    0.06
    otal
    0.06
     tez
    0.06
    Activations Density 0.054%

    No Known Activations