© 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. 126360
    Prev
    Next
    INDEX
    Explanations

    structural elements and definitions in code related to database operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Opening or closing braces in programming code, often defining struct/class definitions, function bodies, or code blocks, usually preceded or followed by whitespace.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
     strokeLine
    -0.06
    atform
    -0.06
    -ind
    -0.06
    .updateDynamic
    -0.06
    ãģ°ãģĭãĤĬ
    -0.06
    ắp
    -0.06
     Taj
    -0.06
    idor
    -0.06
    ener
    -0.06
     "**
    -0.06
    POSITIVE LOGITS
    ÑĢава
    0.07
    vais
    0.06
    Ïĥη
    0.06
    280
    0.06
    kee
    0.06
    fts
    0.06
    ома
    0.05
    adÄĽ
    0.05
    nothrow
    0.05
    ncia
    0.05
    Activations Density 0.004%

    No Known Activations