© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 28371
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and references to ownership

    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
    eniable
    -0.15
     Needle
    -0.14
     Lace
    -0.14
    ebb
    -0.14
     bufsize
    -0.13
    inkel
    -0.13
    ÎŃÏģα
    -0.13
    illez
    -0.13
     herk
    -0.12
    readcr
    -0.12
    POSITIVE LOGITS
     eyes
    0.34
     face
    0.33
     body
    0.33
     hands
    0.32
     head
    0.31
     feet
    0.30
     arms
    0.30
     ears
    0.27
     shoulders
    0.27
     legs
    0.26
    Activations Density 0.117%

    No Known Activations