© 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. 126044
    Prev
    Next
    INDEX
    Explanations

    financial and production metrics in a business context

    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
    uggestions
    -0.06
    ÑİÑĢ
    -0.06
    estruct
    -0.06
    ennie
    -0.06
    ymm
    -0.06
    iali
    -0.06
    õi
    -0.06
    991
    -0.06
    ussy
    -0.06
    afari
    -0.06
    POSITIVE LOGITS
    -cost
    0.06
     ReturnValue
    0.06
     artık
    0.06
     vitam
    0.06
     Beyond
    0.06
     Bowman
    0.06
    decltype
    0.06
    icamente
    0.06
    _less
    0.06
     cost
    0.06
    Activations Density 0.003%

    No Known Activations