© 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. 17-LLAMASCOPE-RES-131K
    11. 117827
    Prev
    Next
    INDEX
    Explanations

    complex relationships and dynamics in narratives involving children, creativity, and interpretations

    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
     various
    -0.11
    åIJĦç§į
    -0.10
     Various
    -0.09
     různ
    -0.08
     escorte
    -0.08
     åIJĦ
    -0.08
     různé
    -0.08
     çeÅŁitli
    -0.08
    rů
    -0.07
    ĥn
    -0.07
    POSITIVE LOGITS
     something
    0.08
    fty
    0.07
     sebuah
    0.07
    ä¸Ģ个
    0.07
    çļĦä¸Ģ个
    0.07
     someone
    0.07
     another
    0.07
     rather
    0.07
    something
    0.07
    ä¸Ģç§į
    0.06
    Activations Density 0.126%

    No Known Activations