© 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. 94841
    Prev
    Next
    INDEX
    Explanations

    references to historical records or documents

    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
     ex
    -0.07
    .Sys
    -0.06
    atrice
    -0.06
    ocket
    -0.06
    illac
    -0.06
    KHR
    -0.06
     exh
    -0.06
    ä¼ij
    -0.06
     muj
    -0.06
     escap
    -0.06
    POSITIVE LOGITS
     household
    0.07
     Enumeration
    0.06
     íķ¨ê»ĺ
    0.06
    apia
    0.06
    iek
    0.06
    ÑĨез
    0.06
    uteur
    0.06
     Bounty
    0.06
     backButton
    0.06
     Household
    0.06
    Activations Density 0.003%

    No Known Activations