© 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. 9-LLAMASCOPE-RES-131K
    11. 97882
    Prev
    Next
    INDEX
    Explanations

    terms related to specific entomological classifications, particularly concerning hymenopteran insects

    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
    heed
    -0.08
    izm
    -0.07
    acha
    -0.07
    ureau
    -0.07
    uggestion
    -0.07
    å¾ĭ
    -0.07
    ibri
    -0.06
    eur
    -0.06
    aurus
    -0.06
    iger
    -0.06
    POSITIVE LOGITS
    lias
    0.07
    ë²ł
    0.06
    eri
    0.06
    akens
    0.06
    isch
    0.06
    ÙĪزÛĮ
    0.06
    -generic
    0.06
     Welch
    0.06
    ibase
    0.06
    ÛĮØ´
    0.06
    Activations Density 0.002%

    No Known Activations