© 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. 5231
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "the" and variations in its usage and 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
    ãĢģãĢģ
    -0.07
     célib
    -0.07
     denen
    -0.07
    Contracts
    -0.06
     Fres
    -0.06
    hev
    -0.06
    ì£ł
    -0.06
     ([]
    -0.06
    ÑĢг
    -0.06
    ä½µ
    -0.06
    POSITIVE LOGITS
    ese
    0.08
    jen
    0.07
    enger
    0.07
     backstage
    0.06
     «
    0.06
    ï¸ı
    0.06
    eyen
    0.06
    añ
    0.06
    оÑĩкÑĥ
    0.06
    mán
    0.06
    Activations Density 0.202%

    No Known Activations