© 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. 31007
    Prev
    Next
    INDEX
    Explanations

    instances of the word "on"

    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
    olo
    -0.08
    ubat
    -0.07
    вол
    -0.07
    pl
    -0.06
    nt
    -0.06
    509
    -0.06
    Ñıм
    -0.06
    ĺìĿ´
    -0.06
    åIJ¾
    -0.06
    erson
    -0.06
    POSITIVE LOGITS
    /off
    0.08
     CONTRIBUTORS
    0.07
     addCriterion
    0.07
    TOTYPE
    0.07
    erialize
    0.07
    icont
    0.07
    .scalablytyped
    0.07
    ìĥĿ
    0.06
     Stir
    0.06
    ymous
    0.06
    Activations Density 0.005%

    No Known Activations