© 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. 98828
    Prev
    Next
    INDEX
    Explanations

    references to sports players and teams

    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
    655
    -0.06
    ç¬
    -0.06
    UST
    -0.06
    нок
    -0.05
    SHIP
    -0.05
     Gonzalez
    -0.05
     lep
    -0.05
    ufen
    -0.05
    usty
    -0.05
    æīįèĥ½
    -0.05
    POSITIVE LOGITS
    иÑĨин
    0.07
    égor
    0.07
    éĺħ读次æķ°
    0.07
    FRING
    0.07
    urance
    0.07
    éra
    0.06
    .breakpoints
    0.06
    ewood
    0.06
    activex
    0.06
    elapsed
    0.06
    Activations Density 0.005%

    No Known Activations