Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43836
    Prev
    Next
    INDEX
    Explanations

    elements related to risk and safety in medical context

    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
    agt
    -0.07
    ediator
    -0.07
    ẹ
    -0.07
    coop
    -0.07
    ORB
    -0.06
    nota
    -0.06
     hometown
    -0.06
    mitt
    -0.06
    phet
    -0.06
    ê
    -0.06
    POSITIVE LOGITS
     science
    0.09
     Regulation
    0.09
     Regulatory
    0.09
     regulators
    0.08
     regulatory
    0.08
     Science
    0.08
     regulation
    0.08
     scientific
    0.08
     scient
    0.08
     "...
    0.07
    Activations Density 0.008%

    No Known Activations