© 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. 70919
    Prev
    Next
    INDEX
    Explanations

    imperative verbs and phrases related to medical procedures and biological processes

    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
    огÑĥ
    -0.07
    uchi
    -0.07
    ena
    -0.07
    á»ķ
    -0.06
    889
    -0.06
    outu
    -0.06
     mortar
    -0.06
    vat
    -0.06
     migrations
    -0.06
     french
    -0.06
    POSITIVE LOGITS
     anonymously
    0.08
     altru
    0.08
     gön
    0.07
    uyá»ĩn
    0.07
     åĮ
    0.07
     Haram
    0.07
    æ
    0.06
     donors
    0.06
     pseud
    0.06
     anonymous
    0.06
    Activations Density 0.000%

    No Known Activations