© 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. 92075
    Prev
    Next
    INDEX
    Explanations

    specific names, types, and references that relate to locations or events associated with various entities or themes

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

    Initial letters or segments of proper names, location identifiers, and technical terms that appear in structured listings, catalogs, or bibliographic data.

    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
     Dich
    -0.06
    checkBox
    -0.06
    važ
    -0.06
    имÑĥ
    -0.06
    ISIS
    -0.06
    Ìģt
    -0.06
    getPlayer
    -0.05
    arith
    -0.05
    辺
    -0.05
    (unittest
    -0.05
    POSITIVE LOGITS
    -thumbnails
    0.07
    -animate
    0.07
    nip
    0.07
     Shields
    0.07
    edeki
    0.07
    istrovstvÃŃ
    0.06
    obar
    0.06
    disposing
    0.06
    ãĤ¬
    0.06
     genu
    0.06
    Activations Density 0.008%

    No Known Activations