© 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. 126914
    Prev
    Next
    INDEX
    Explanations

    references to feeding behavior and dietary habits of animals

    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
    hea
    -0.07
    ìļ©
    -0.07
    баÑģ
    -0.07
    escape
    -0.07
    erno
    -0.07
    asics
    -0.06
    ãĥªãĥ¼ãĤº
    -0.06
     Integrity
    -0.06
    elsea
    -0.06
    antity
    -0.06
    POSITIVE LOGITS
     diet
    0.08
     Opport
    0.08
     food
    0.07
    é£Ł
    0.07
    /XMLSchema
    0.07
     opportun
    0.07
    iena
    0.07
    -food
    0.07
     opport
    0.06
     intake
    0.06
    Activations Density 0.009%

    No Known Activations