© 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. 81711
    Prev
    Next
    INDEX
    Explanations

    references to authors or contributors in written works

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

    Citation-related elements including author attribution markers ("by"), connector words between multiple authors ("and", "&"), punctuation marks in formal citations (":"), and text that introduces lists or content.

    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
    âĢ¦↵
    -0.13
    âĢ¦”
    -0.10
     âĢ¦↵
    -0.08
     [âĢ¦]↵
    -0.08
    -Compatible
    -0.07
    ..↵
    -0.07
    ,...↵
    -0.07
    /Foundation
    -0.07
     [âĢ¦
    -0.07
    Âłin
    -0.06
    POSITIVE LOGITS
    .Reporting
    0.12
     знов
    0.11
     ayn
    0.10
    çĽijåIJ¬é¡µéĿ¢
    0.09
     lah
    0.09
     VÅ¡ech
    0.09
     Ù¾Úĺ
    0.09
    _REF
    0.09
     ==============================================================
    0.09
     впол
    0.09
    Activations Density 0.266%

    No Known Activations