© 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. 117079
    Prev
    Next
    INDEX
    Explanations

    phrases related to failed operations or interventions in a medical or institutional 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
    etwork
    -0.07
    baum
    -0.06
    gra
    -0.06
    Ìī
    -0.06
     nuts
    -0.05
     ç¨
    -0.05
     figures
    -0.05
    ima
    -0.05
     sky
    -0.05
    //---------------------------------------------------------------------------↵↵
    -0.05
    POSITIVE LOGITS
    uyo
    0.08
    VERR
    0.07
    .Bunifu
    0.07
    à¸Ńว
    0.07
    ugo
    0.07
    (:,:,
    0.07
    ande
    0.06
    εί
    0.06
     Charm
    0.06
    aday
    0.06
    Activations Density 0.001%

    No Known Activations