© 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. 29119
    Prev
    Next
    INDEX
    Explanations

    collocations involving coordination or connection of ideas

    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
    лаж
    -0.06
     Chill
    -0.06
    rana
    -0.06
    emple
    -0.06
     addCriterion
    -0.05
    hen
    -0.05
    æ¢
    -0.05
    rica
    -0.05
    raÄį
    -0.05
     McA
    -0.05
    POSITIVE LOGITS
     tip
    0.08
    .tip
    0.07
     tips
    0.07
     ë°°ìļ°
    0.06
    tip
    0.06
    ¡´
    0.06
     Sé
    0.06
     Passport
    0.06
    flare
    0.06
    ÙħاÙĨÛĮ
    0.06
    Activations Density 0.000%

    No Known Activations