© 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. 14937
    Prev
    Next
    INDEX
    Explanations

    mentions of API calls or references to actions within the API 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
    ewater
    -0.06
     Kis
    -0.05
     channel
    -0.05
    ASSES
    -0.05
    oney
    -0.05
     discriminate
    -0.05
    th
    -0.05
     Skinner
    -0.05
    ,
    -0.05
     Integrated
    -0.05
    POSITIVE LOGITS
    .scalablytyped
    0.09
    istrovstvÃŃ
    0.07
    opis
    0.07
    inds
    0.07
    ijk
    0.07
    /GPL
    0.07
    _PS
    0.07
    æħİ
    0.07
    çak
    0.07
    routine
    0.07
    Activations Density 0.000%

    No Known Activations