© 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. 57124
    Prev
    Next
    INDEX
    Explanations

    technical terminology and data structures in scientific or programming contexts

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

    Common technical and programming syntax elements that appear in code, mathematical notation, or structured technical documentation.

    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
    etwork
    -0.07
    zap
    -0.06
    oreach
    -0.06
    zcze
    -0.06
    OfWork
    -0.06
    alth
    -0.06
     bacheca
    -0.06
    ãģĩ
    -0.06
    accent
    -0.06
    ẩu
    -0.06
    POSITIVE LOGITS
    ×Ļ×
    0.10
     Ä°
    0.08
    িà¦
    0.08
    ிà®
    0.07
    $I
    0.07
    ]int
    0.07
     à¤ĩ
    0.07
    ISyntaxException
    0.07
    $i
    0.07
    ingham
    0.07
    Activations Density 0.543%

    No Known Activations