© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 88179
    Prev
    Next
    INDEX
    Explanations

    code structures related to module exports in JavaScript

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ette
    -0.07
    ire
    -0.07
    ul
    -0.06
    f
    -0.06
    lasses
    -0.06
    aval
    -0.06
    ros
    -0.06
    ama
    -0.06
    iba
    -0.06
    to
    -0.06
    POSITIVE LOGITS
    acerb
    0.07
    agher
    0.07
    OffsetTable
    0.07
    azer
    0.07
    .UnitTesting
    0.07
    /WebAPI
    0.07
    /lic
    0.07
     =↵↵
    0.07
    anter
    0.06
    \grid
    0.06
    Activations Density 0.001%

    No Known Activations