© 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. 78495
    Prev
    Next
    INDEX
    Explanations

    verbs and phrases related to visual engagement and exploration

    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
    egasus
    -0.06
    wear
    -0.06
    MUX
    -0.06
    ogonal
    -0.06
    hek
    -0.06
    urge
    -0.06
    ideos
    -0.06
     Shelter
    -0.06
    icism
    -0.05
    uze
    -0.05
    POSITIVE LOGITS
    Çİ
    0.07
    arend
    0.07
    ffen
    0.07
    ÐļТ
    0.06
    ulis
    0.06
    ean
    0.06
    ebin
    0.06
    opping
    0.06
    ighter
    0.06
     erotisch
    0.06
    Activations Density 0.001%

    No Known Activations