© 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. 70972
    Prev
    Next
    INDEX
    Explanations

    instances of programming language syntax or directive statements

    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
    enko
    -0.08
    loff
    -0.08
    ãĥ¼ãĥij
    -0.08
    loating
    -0.08
    creativecommons
    -0.08
    ingleton
    -0.08
    akov
    -0.07
    διο
    -0.07
    oodles
    -0.07
    velope
    -0.07
    POSITIVE LOGITS
    &
    0.06
    itan
    0.06
    nd
    0.06
     Kend
    0.06
    era
    0.06
    ked
    0.06
    iv
    0.05
     voc
    0.05
     batt
    0.05
    ref
    0.05
    Activations Density 0.000%

    No Known Activations