© 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. 55778
    Prev
    Next
    INDEX
    Explanations

    references to health, wellness, and the body's needs

    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
    uraa
    -0.07
    trap
    -0.07
     faults
    -0.06
    ampaign
    -0.06
    ToWorld
    -0.06
     developmental
    -0.06
     Horm
    -0.06
    .addRow
    -0.06
    .getClassName
    -0.06
     SS
    -0.06
    POSITIVE LOGITS
     relief
    0.09
     Relief
    0.08
     instant
    0.07
     stripslashes
    0.07
    incy
    0.07
     soothing
    0.06
    äs
    0.06
    patches
    0.06
    olley
    0.06
     patches
    0.06
    Activations Density 0.002%

    No Known Activations