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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 22-LLAMASCOPE-RES-131K
    6. 5264
    Prev
    Next
    INDEX
    Explanations

    skin care and cosmetic application recommendations

    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
    hoff
    -0.07
    agr
    -0.07
    LEAN
    -0.06
    jh
    -0.06
     cleanup
    -0.06
     shaken
    -0.06
     tooth
    -0.06
    essor
    -0.06
     Blade
    -0.06
     vidé
    -0.06
    POSITIVE LOGITS
     moistur
    0.12
     moisture
    0.11
     Moist
    0.10
     barrier
    0.10
     ker
    0.10
     Derm
    0.10
    Barrier
    0.10
     Ker
    0.09
     Barrier
    0.09
     hydration
    0.09
    Activations Density 0.006%

    No Known Activations