© 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. 82379
    Prev
    Next
    INDEX
    Explanations

    scientific classifications and taxonomic hierarchy within biological 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
    riad
    -0.07
    azu
    -0.07
    ultan
    -0.07
     Dün
    -0.07
    kad
    -0.07
    изнеÑģ
    -0.07
    (pi
    -0.07
    rlen
    -0.07
    à¸ļà¸Ĺ
    -0.07
     kapas
    -0.07
    POSITIVE LOGITS
     division
    0.08
     sub
    0.08
     section
    0.07
     Division
    0.07
     subdivision
    0.06
     Section
    0.06
     ambit
    0.06
     Ore
    0.06
     group
    0.06
     divis
    0.06
    Activations Density 0.019%

    No Known Activations