© 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. 95462
    Prev
    Next
    INDEX
    Explanations

    inquiries and requests for explanations or assistance

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

    Polite request phrases in online help-seeking contexts where users ask others for explanations, clarification, or advice.

    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
    ump
    -0.07
    els
    -0.06
    ald
    -0.06
    ugs
    -0.06
    phin
    -0.06
     Hut
    -0.06
    ked
    -0.05
     eas
    -0.05
     Gord
    -0.05
    already
    -0.05
    POSITIVE LOGITS
     please
    0.09
    ä¸Ģä¸ĭ
    0.09
     PLEASE
    0.08
    please
    0.07
    GGLE
    0.07
    icion
    0.07
    isku
    0.07
    让æĪij
    0.07
    çŃĭ
    0.07
     example
    0.07
    Activations Density 0.008%

    No Known Activations