© 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. 117833
    Prev
    Next
    INDEX
    Explanations

    instances of the word "that" and related phrases

    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
    екÑģи
    -0.08
    okit
    -0.07
    empo
    -0.07
    isÃŃ
    -0.07
    ì°Į
    -0.07
    raquo
    -0.07
     addCriterion
    -0.07
     ÑģоÑģÑĤоÑı
    -0.07
    .EMPTY
    -0.07
    eya
    -0.07
    POSITIVE LOGITS
    clas
    0.07
     cannot
    0.06
    535
    0.06
    uky
    0.06
    sworth
    0.06
    fav
    0.06
     exploit
    0.06
     none
    0.06
     few
    0.05
     exploiting
    0.05
    Activations Density 0.040%

    No Known Activations