© 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. 124358
    Prev
    Next
    INDEX
    Explanations

    the name "Julian" and its variations

    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
    edly
    -0.08
    uffman
    -0.07
    elijke
    -0.07
    elon
    -0.07
    el
    -0.07
    kv
    -0.07
    avy
    -0.07
    .ReadString
    -0.07
    gable
    -0.06
    aldi
    -0.06
    POSITIVE LOGITS
    opsis
    0.07
    pedia
    0.07
    mente
    0.07
    ities
    0.07
    ized
    0.07
    isiert
    0.07
    åĪ¥
    0.07
    Ñĩик
    0.07
    laÅŁ
    0.07
    ovsky
    0.07
    Activations Density 0.004%

    No Known Activations