© 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. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 24672
    Prev
    Next
    INDEX
    Explanations

    concepts related to ownership and personal agency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Juliushanhanhan/llama-3-8b-it-res/blocks.25.hook_resid_post
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    gated
    Context Size
    1,024
    Dataset
    Juliushanhanhan/openwebtext-1b-llama3-tokenized-cxt-1024
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Both
    -0.17
     both
    -0.16
    Å¡ov
    -0.15
    ISIBLE
    -0.15
    Both
    -0.14
    aras
    -0.14
    /vnd
    -0.13
    ä¸Ķ
    -0.13
     BOTH
    -0.13
    à¸Ļà¸Ń
    -0.13
    POSITIVE LOGITS
     certain
    0.76
     particular
    0.65
    æŁIJ
    0.60
     Certain
    0.58
    Certain
    0.56
     specific
    0.48
    ertain
    0.48
     certains
    0.47
     bestimm
    0.46
     various
    0.40
    Activations Density 0.234%

    No Known Activations