© 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. 16433
    Prev
    Next
    INDEX
    Explanations

    expressions of artistic representation and critique

    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
    ếu
    -0.07
    weetalert
    -0.07
    LTR
    -0.07
    ÑĢок
    -0.07
    InSection
    -0.07
    æĨ
    -0.06
    /Area
    -0.06
    566
    -0.06
     Magick
    -0.06
    748
    -0.06
    POSITIVE LOGITS
     how
    0.09
     what
    0.08
     both
    0.07
     exactly
    0.06
     the
    0.06
     typical
    0.06
    cone
    0.06
     cond
    0.06
     why
    0.06
     Ñģобой
    0.06
    Activations Density 0.027%

    No Known Activations