© 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. 87608
    Prev
    Next
    INDEX
    Explanations

    instructions related to skin care and cleaning routines

    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
    ond
    -0.07
    rette
    -0.07
    ustil
    -0.07
    usting
    -0.07
    idget
    -0.07
     bì
    -0.06
    BASH
    -0.06
    ucht
    -0.06
    ивÑĪи
    -0.06
     ust
    -0.06
    POSITIVE LOGITS
    witter
    0.07
     bor
    0.07
     followed
    0.07
    otti
    0.06
     Optional
    0.06
    avig
    0.06
     final
    0.06
    418
    0.06
    630
    0.06
     FINAL
    0.06
    Activations Density 0.014%

    No Known Activations