© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 1831
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals and their roles or actions

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

    Three-letter tokens that represent the end parts of proper nouns, technical terms, slang, or specialized vocabulary in different domains - including people's nicknames (oz, oba), animal sounds/parts (roe, frogs), technical abbreviations (VOB, DOA), offensive slurs (wogs, hoes), place names (Sogo), technical parameters (STOW), and technical objects (Koi, hoe).

    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
    ucci
    -0.10
    'ın
    -0.08
    eview
    -0.07
    mony
    -0.07
    roots
    -0.07
    oretical
    -0.07
    quisitions
    -0.07
    urally
    -0.07
    acons
    -0.07
    stoup
    -0.07
    POSITIVE LOGITS
    yssey
    0.09
    theast
    0.09
    ìį¨
    0.09
    ÌĪ
    0.09
     Angeles
    0.09
    ÑģÑıг
    0.08
    naments
    0.08
    sett
    0.08
    annes
    0.08
    olulu
    0.08
    Activations Density 0.392%

    No Known Activations