© 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. 73647
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical objects or experiences, particularly those related to games or sports

    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
    ErrorHandler
    -0.07
    اÙģÙĩ
    -0.06
    ouro
    -0.06
    ãĤ¤ãĤ¯
    -0.06
     tầm
    -0.06
     sav
    -0.06
     Daemon
    -0.06
     FUCK
    -0.06
    åŀ
    -0.06
    zl
    -0.06
    POSITIVE LOGITS
     bath
    0.08
    opot
    0.07
     itself
    0.06
    å«Į
    0.06
    ularity
    0.06
    /XMLSchema
    0.06
    dance
    0.06
    çľ
    0.06
     Bath
    0.06
    ossier
    0.06
    Activations Density 0.102%

    No Known Activations