© 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 EvalsExportsAPI 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. 59338
    Prev
    Next
    INDEX
    Explanations

    references to specific items or concepts related to locations, activities, and items

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

    Specific nouns representing objects, products, services, or specialized domains that are the central subject of informational or descriptive 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
    _COMPILE
    -0.06
    iaz
    -0.06
    DBC
    -0.06
    .scalablytyped
    -0.06
    ylland
    -0.06
     Morr
    -0.06
    renal
    -0.06
    omial
    -0.05
     id
    -0.05
    imuth
    -0.05
    POSITIVE LOGITS
     ®
    0.08
    еди
    0.07
    weed
    0.07
     erotische
    0.06
    lean
    0.06
    usher
    0.06
    ouch
    0.06
    /../
    0.06
    leh
    0.06
    ÑĪÑĤ
    0.06
    Activations Density 1.779%

    No Known Activations