© 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. 15-LLAMASCOPE-RES-131K
    6. 103595
    Prev
    Next
    INDEX
    Explanations

    content related to events, schedules, and procedural information

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

    Programming language control structures and syntax elements, particularly preprocessor directives like "#if" and common code patterns, along with parser-specific tokens and structural elements that appear in various programming contexts.

    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
    816
    -0.07
    716
    -0.06
    548
    -0.06
    759
    -0.06
    714
    -0.06
    715
    -0.06
    091
    -0.06
    ilar
    -0.06
    616
    -0.06
    778
    -0.06
    POSITIVE LOGITS
    edException
    0.07
    dit
    0.07
    CISION
    0.07
    &uuml
    0.07
    aData
    0.07
     Dit
    0.07
     Fav
    0.07
     Spicer
    0.06
    ìĹŃìĭľ
    0.06
    rek
    0.06
    Activations Density 0.297%

    No Known Activations