© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 3431
    Prev
    Next
    INDEX
    Explanations

    indicators of product quality and consumer behavior in the dairy market

    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
     stub
    -0.06
    ectl
    -0.06
    ики
    -0.06
    isher
    -0.06
     al
    -0.06
     Automobile
    -0.06
     overseas
    -0.06
     Warehouse
    -0.06
     Writer
    -0.06
    olio
    -0.05
    POSITIVE LOGITS
    див
    0.07
    krv
    0.07
    ivec
    0.07
    LEAN
    0.07
     saja
    0.07
    ovnÃŃ
    0.06
     lep
    0.06
    ATAB
    0.06
    ined
    0.06
    irma
    0.06
    Activations Density 0.002%

    No Known Activations