© 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. 95798
    Prev
    Next
    INDEX
    Explanations

    references to various cultures, regions, or identities related to music or art

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

    Punctuation (commas) and conjunctions ("and") that separate items in lists of proper nouns, technical terms, or named entities.

    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
    -0.08
    ìį¨
    -0.08
    .backward
    -0.07
     знов
    -0.07
    agu
    -0.07
    plex
    -0.07
    تاÙĨ
    -0.07
    Gear
    -0.07
     trÃŃ
    -0.07
     dahi
    -0.07
    POSITIVE LOGITS
    /or
    0.07
    oku
    0.06
    ersen
    0.06
     etc
    0.06
    etc
    0.06
     others
    0.06
     downright
    0.06
    utterstock
    0.06
    äre
    0.06
    /Foundation
    0.06
    Activations Density 0.211%

    No Known Activations