© 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. 15-LLAMASCOPE-RES-131K
    11. 86477
    Prev
    Next
    INDEX
    Explanations

    scientific classifications and common names of species, particularly plants and animals

    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
    -www
    -0.06
    Ñģи
    -0.06
     otel
    -0.06
    ghan
    -0.06
    icide
    -0.06
    Legend
    -0.06
     Pon
    -0.06
    undy
    -0.06
     Garn
    -0.06
    504
    -0.06
    POSITIVE LOGITS
    anche
    0.07
    URES
    0.07
    owi
    0.07
    ترÛĮ
    0.07
     deferred
    0.06
    ει
    0.06
    quam
    0.06
     Filed
    0.06
     Naked
    0.06
     Freel
    0.06
    Activations Density 0.013%

    No Known Activations