© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 56451
    Prev
    Next
    INDEX
    Explanations

    references to biocatalysts and enzymatic processes in the context of pharmaceutical development

    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
     conna
    -0.07
    -os
    -0.07
    cean
    -0.07
    gis
    -0.07
     kabil
    -0.07
     vaz
    -0.07
    edla
    -0.06
    bakan
    -0.06
    رس
    -0.06
     gratuits
    -0.06
    POSITIVE LOGITS
     your
    0.11
    your
    0.10
     YOUR
    0.09
    ă
    0.08
     ваÑĪ
    0.08
     either
    0.08
    ä½łçļĦ
    0.08
    Your
    0.07
     votre
    0.07
    either
    0.07
    Activations Density 0.034%

    No Known Activations