© 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. 1164
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and actions

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

    Special characters or tokens that appear in code snippets, code errors, or programming contexts - including file extensions, code syntax elements (like periods before method calls), version numbers, date components in logs, or command terminators in various programming languages.

    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
    nah
    -0.06
    iler
    -0.06
    -cache
    -0.06
    à¹Ĥà¸Ĺ
    -0.06
    íĬ
    -0.06
    ÄĽÅĻ
    -0.06
    -tm
    -0.06
    zb
    -0.06
    âĦ
    -0.06
     Leh
    -0.06
    POSITIVE LOGITS
    inker
    0.08
    ommen
    0.07
    engo
    0.06
    åĩĨ
    0.06
    iage
    0.06
     Sext
    0.06
     Ambient
    0.06
     tük
    0.06
     ÎĶε
    0.06
    amedi
    0.05
    Activations Density 0.006%

    No Known Activations