© 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 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. 128843
    Prev
    Next
    INDEX
    Explanations

    words that represent the term "Caesar."

    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
    го
    -0.07
    argent
    -0.06
    visor
    -0.06
    enheim
    -0.06
     Cabr
    -0.06
    æij©
    -0.06
    меÑĢик
    -0.06
    âĶIJ
    -0.06
    à¸Ĥ
    -0.06
    gebra
    -0.06
    POSITIVE LOGITS
    /ca
    0.09
    iflower
    0.09
    esar
    0.07
    uti
    0.07
    ucas
    0.07
     caution
    0.07
    INET
    0.07
     ca
    0.06
    unky
    0.06
     lift
    0.06
    Activations Density 0.016%

    No Known Activations