© 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. 70308
    Prev
    Next
    INDEX
    Explanations

    syntax-related elements or structures in code

    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
    veau
    -0.07
    tractor
    -0.07
    itu
    -0.07
    odcast
    -0.07
    claimer
    -0.07
    rch
    -0.06
    ",-
    -0.06
    //[
    -0.06
    igne
    -0.06
    iton
    -0.06
    POSITIVE LOGITS
    zano
    0.09
     springfox
    0.06
     ?,
    0.06
    adal
    0.06
    odore
    0.06
     Nie
    0.06
    locker
    0.06
     )↵↵↵↵↵↵↵↵
    0.06
    orsk
    0.06
     Pic
    0.06
    Activations Density 0.007%

    No Known Activations