© 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. 74725
    Prev
    Next
    INDEX
    Explanations

    references to skin care and treatment instructions

    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
     poisonous
    -0.06
    addock
    -0.06
     newSize
    -0.06
     preorder
    -0.06
    ìĤ¬ìĿ´
    -0.06
    leanup
    -0.06
    ź
    -0.06
    shake
    -0.06
     weights
    -0.06
     Tooth
    -0.06
    POSITIVE LOGITS
     winter
    0.10
     Winter
    0.09
     moistur
    0.08
     harsh
    0.07
    Winter
    0.07
     skin
    0.07
     Skin
    0.07
     Derm
    0.07
    rak
    0.07
     dry
    0.07
    Activations Density 0.016%

    No Known Activations