© 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. 15-LLAMASCOPE-RES-131K
    11. 90383
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and structure elements

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

    Code-related tokens that indicate method/property getters ("get"), parameter names with opening parenthesis ("("), specialized names or identifiers in programming contexts ("tab", "PASS", "response", "ColumnType", "CHECK"), or specific programming syntactic elements like "::" in C++ scope resolution.

    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
    owski
    -0.07
     Wilkinson
    -0.06
    çĨ
    -0.06
    olas
    -0.06
    berger
    -0.06
    \↵
    -0.06
     Kah
    -0.06
     Aynı
    -0.06
    ढ
    -0.06
    貨
    -0.06
    POSITIVE LOGITS
    alars
    0.09
     sonst
    0.08
    zeigen
    0.07
    undry
    0.07
     기íĥĢ
    0.07
    exampleInput
    0.07
    _misc
    0.07
     ãģĿãģ®ä»ĸ
    0.07
    ãģĿãģ®ä»ĸ
    0.07
    etc
    0.07
    Activations Density 0.050%

    No Known Activations