© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 88471
    Prev
    Next
    INDEX
    Explanations

    code-related operations and function calls

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

    Variable, function, or object references in code, often part of method calls, property access, or parameter names across multiple programming languages including C++, PHP, JavaScript, and specialized frameworks.

    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
    å¤Ħ
    -0.06
    иÑģлов
    -0.06
    üçük
    -0.06
    /goto
    -0.06
    emez
    -0.06
    à¹Ģà¸Ī
    -0.06
    gado
    -0.06
    odo
    -0.06
    üç
    -0.05
     False
    -0.05
    POSITIVE LOGITS
    tps
    0.06
     _
    0.06
    \_
    0.06
    EK
    0.06
    roat
    0.06
    éri
    0.06
    å¢
    0.06
    auc
    0.06
    StatusLabel
    0.06
    omnia
    0.06
    Activations Density 0.237%

    No Known Activations