© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 86674
    Prev
    Next
    INDEX
    Explanations

    information about influential roles and decision-makers 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
    ainer
    -0.07
    uell
    -0.07
    οι
    -0.07
    orent
    -0.07
    ainter
    -0.06
     Fold
    -0.06
    raya
    -0.06
    Æ¡n
    -0.06
     Oversight
    -0.06
    Fold
    -0.06
    POSITIVE LOGITS
     decision
    0.09
     chief
    0.08
     budgets
    0.08
     purchasing
    0.08
     heads
    0.08
     senior
    0.08
     executives
    0.08
    decision
    0.07
     Decision
    0.07
    -chief
    0.07
    Activations Density 0.017%

    No Known Activations