© 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. 30622
    Prev
    Next
    INDEX
    Explanations

    specific game-related terms and activities

    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
    icket
    -0.08
    zzo
    -0.08
    subst
    -0.07
    hack
    -0.07
    rive
    -0.07
    лива
    -0.07
    mentation
    -0.06
    oins
    -0.06
    kek
    -0.06
    encer
    -0.06
    POSITIVE LOGITS
    -playing
    0.08
    -esque
    0.07
    -like
    0.07
    ufreq
    0.07
    aur
    0.07
    istan
    0.06
    board
    0.06
    λε
    0.06
    AdapterFactory
    0.06
    oleon
    0.06
    Activations Density 0.021%

    No Known Activations