© 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. 86360
    Prev
    Next
    INDEX
    Explanations

    references to literary works and authors

    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
     Roosevelt
    -0.07
    /gin
    -0.07
     Lange
    -0.06
     Michigan
    -0.06
    yx
    -0.06
    assy
    -0.06
    Michigan
    -0.06
     Bourbon
    -0.06
    @js
    -0.06
     Chic
    -0.06
    POSITIVE LOGITS
     Blake
    0.09
    Blake
    0.09
    lyph
    0.07
     polar
    0.07
     gest
    0.07
    ÑĢаÑĩ
    0.06
     Sanat
    0.06
     interp
    0.06
    kova
    0.06
     Clamp
    0.06
    Activations Density 0.003%

    No Known Activations