© 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. 54261
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notations in a formal proof context

    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
     Bene
    -0.07
    ipa
    -0.07
    ulty
    -0.06
     Barcl
    -0.06
    BorderStyle
    -0.06
    bew
    -0.06
     Ruth
    -0.06
     SaÄŁ
    -0.06
    opot
    -0.06
     Hunt
    -0.06
    POSITIVE LOGITS
    203
    0.06
    izen
    0.06
    ÑĤÑĥÑĢа
    0.06
    غة
    0.06
    ÑĢован
    0.06
     ((__
    0.06
    prd
    0.06
    AsyncResult
    0.06
    zek
    0.06
    488
    0.06
    Activations Density 0.461%

    No Known Activations