© 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. 62132
    Prev
    Next
    INDEX
    Explanations

    references to locations and origins

    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
    enden
    -0.07
    angling
    -0.06
     شع
    -0.06
    atos
    -0.06
    ucha
    -0.06
    ÅĽnie
    -0.06
    ì²Ń
    -0.06
    azzi
    -0.06
     Buen
    -0.06
    atern
    -0.06
    POSITIVE LOGITS
     Bordeaux
    0.10
     Memphis
    0.08
     Shelby
    0.08
     Lagos
    0.08
     LSU
    0.07
     Mississippi
    0.07
     leve
    0.07
    clair
    0.07
     imp
    0.07
    BAT
    0.07
    Activations Density 0.002%

    No Known Activations