© 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. 9-LLAMASCOPE-RES-131K
    11. 98122
    Prev
    Next
    INDEX
    Explanations

    references to poker games and related terminology

    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
    бÑĢа
    -0.06
    ext
    -0.06
    æķ·
    -0.06
     fashion
    -0.06
    omid
    -0.06
    eus
    -0.05
     pans
    -0.05
    HEMA
    -0.05
    LC
    -0.05
    437
    -0.05
    POSITIVE LOGITS
    tron
    0.07
    imli
    0.07
     Strip
    0.07
     Haram
    0.07
     Sapphire
    0.07
    ergic
    0.06
    ordes
    0.06
    afil
    0.06
     simult
    0.06
     Arnold
    0.06
    Activations Density 0.001%

    No Known Activations