© 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. 104730
    Prev
    Next
    INDEX
    Explanations

    the name "Katie" in various contexts throughout the text

    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
     defaultMessage
    -0.08
    Hit
    -0.07
    rate
    -0.07
    etine
    -0.07
    ignment
    -0.07
    #__
    -0.07
    cht
    -0.07
    raq
    -0.07
    rias
    -0.07
    ardi
    -0.07
    POSITIVE LOGITS
    undry
    0.06
    fer
    0.06
    embro
    0.06
    legg
    0.06
    arges
    0.06
    овоÑĢ
    0.06
    gos
    0.06
    agan
    0.06
    istic
    0.05
    ees
    0.05
    Activations Density 0.003%

    No Known Activations