© 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. 94891
    Prev
    Next
    INDEX
    Explanations

    expressions and descriptions related to close-up images or details in visual content

    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
    andler
    -0.07
    edException
    -0.07
    apel
    -0.07
    ascript
    -0.06
    baum
    -0.06
    áng
    -0.06
    ivol
    -0.06
    rol
    -0.06
     Noon
    -0.06
    ufs
    -0.06
    POSITIVE LOGITS
    rawl
    0.07
    /stdc
    0.07
    .partial
    0.06
     Wilkinson
    0.06
    ieux
    0.06
     Wah
    0.06
     Woodward
    0.06
    ÛĮا
    0.06
    HORT
    0.06
    ÛĮÚ©ÛĮ
    0.06
    Activations Density 0.004%

    No Known Activations