© 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. 82371
    Prev
    Next
    INDEX
    Explanations

    terms that relate to various forms of art, literature, and ethical or cultural discussions

    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
     PIXI
    -0.07
    Å¡t
    -0.07
    êµ
    -0.07
    ory
    -0.07
    firm
    -0.07
    istrovstvÃŃ
    -0.06
    LError
    -0.06
    oria
    -0.06
    alten
    -0.06
    chyb
    -0.06
    POSITIVE LOGITS
    uttle
    0.08
    roulette
    0.07
    bairro
    0.06
    /math
    0.06
    mith
    0.06
    osite
    0.06
    EFR
    0.06
    -social
    0.06
     conse
    0.06
    WithValue
    0.06
    Activations Density 0.046%

    No Known Activations