© 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. 76732
    Prev
    Next
    INDEX
    Explanations

    references to dietary recommendations and individual factors affecting health

    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
    ÌĨ
    -0.08
    abr
    -0.07
    umph
    -0.07
    ritel
    -0.07
    vale
    -0.06
    |string
    -0.06
    .dds
    -0.06
    umar
    -0.06
    Overflow
    -0.06
    iosis
    -0.06
    POSITIVE LOGITS
     weight
    0.09
     body
    0.08
     Body
    0.07
     BODY
    0.07
     energy
    0.07
     daily
    0.06
    weight
    0.06
    activity
    0.06
    ä½ĵ
    0.06
    Body
    0.06
    Activations Density 0.012%

    No Known Activations