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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 60006
    Prev
    Next
    INDEX
    Explanations

    references to television shows and viewing habits

    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
     toe
    -0.06
    ancia
    -0.06
    (HttpContext
    -0.06
    irit
    -0.06
    ÑĢик
    -0.06
     IR
    -0.05
     Irving
    -0.05
    -0.05
     unto
    -0.05
    ims
    -0.05
    POSITIVE LOGITS
     opportunity
    0.09
     offered
    0.09
    _AVAILABLE
    0.08
     offer
    0.08
    available
    0.08
     available
    0.07
     offering
    0.07
     offerings
    0.07
    Offer
    0.07
    stad
    0.07
    Activations Density 0.086%

    No Known Activations