© 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. 130843
    Prev
    Next
    INDEX
    Explanations

    phrases indicating adjustments or modifications being made to something

    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
    laughter
    -0.08
    usat
    -0.07
    ór
    -0.07
    лей
    -0.06
     sharp
    -0.06
    Sharp
    -0.06
     ìĿ´ë¯¸
    -0.06
    ule
    -0.06
    ãĥĥ
    -0.06
     cuffs
    -0.06
    POSITIVE LOGITS
    æĽ´åĬł
    0.07
     Äijỡ
    0.07
     more
    0.07
    æĽ´
    0.07
    indow
    0.06
     lebih
    0.06
    echa
    0.06
     Enlight
    0.06
     Sparks
    0.06
    egra
    0.06
    Activations Density 0.041%

    No Known Activations