© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 78790
    Prev
    Next
    INDEX
    Explanations

    structured programming elements, particularly function definitions and returns

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

    Closing tokens (parentheses, brackets) or return expressions at the end of code blocks, function calls, or method definitions, usually followed by a new code section.

    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
    954
    -0.07
    loven
    -0.07
    ulum
    -0.07
    eÅŁit
    -0.07
    ul
    -0.07
    dit
    -0.06
    addtogroup
    -0.06
     subdir
    -0.06
    ulp
    -0.06
    rž
    -0.06
    POSITIVE LOGITS
    ắn
    0.07
    459
    0.06
    aukee
    0.06
    kowski
    0.06
    pbs
    0.06
     TextAlign
    0.06
    andr
    0.06
    psz
    0.06
    sink
    0.06
    £¼
    0.06
    Activations Density 0.074%

    No Known Activations