© 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 EvalsExportsinterp-engineNEWAPI 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. 42047
    Prev
    Next
    INDEX
    Explanations

    procedural content related to applications and processes

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

    A correctly placed comma that separates clauses or introduces dependent clauses, often before conjunctions like "that", "so", or "you" when they connect related thoughts or introduce explanations.

    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
     involved
    -0.06
    ëłĪìĿ´
    -0.06
    ijkstra
    -0.05
    iras
    -0.05
    entai
    -0.05
    .ensure
    -0.05
    -demand
    -0.05
    ira
    -0.05
    dana
    -0.05
     demanded
    -0.05
    POSITIVE LOGITS
     можно
    0.15
    åı¯ä»¥
    0.14
     can
    0.14
     можна
    0.12
    ï¼Įåı¯ä»¥
    0.11
     puedes
    0.11
     można
    0.11
    can
    0.11
     ÙĬÙħÙĥÙĨ
    0.11
     můžete
    0.11
    Activations Density 0.113%

    No Known Activations