© 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. 58464
    Prev
    Next
    INDEX
    Explanations

    terms related to recognition and distinction in various contexts

    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
    gba
    -0.07
    utin
    -0.07
     Fold
    -0.07
    ÄĽti
    -0.07
     terrestrial
    -0.06
     forks
    -0.06
    á»ķng
    -0.06
    amon
    -0.06
    ukt
    -0.06
    ávÄĽ
    -0.06
    POSITIVE LOGITS
     reput
    0.08
    ingly
    0.07
    icer
    0.07
    çĪ
    0.07
     marginal
    0.07
     amongst
    0.06
     reputation
    0.06
     propag
    0.06
     contribution
    0.06
    Among
    0.06
    Activations Density 0.037%

    No Known Activations