Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 29295
    Prev
    Next
    INDEX
    Explanations

    references to notable individuals and their careers in sports

    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
    otton
    -0.17
    imens
    -0.14
    ensex
    -0.14
    fprintf
    -0.14
    stakes
    -0.14
    awe
    -0.14
    غاÙĦ
    -0.14
     viewport
    -0.14
     Slate
    -0.14
    antis
    -0.14
    POSITIVE LOGITS
     playing
    0.63
     plays
    0.54
     play
    0.53
     played
    0.53
     Playing
    0.52
    playing
    0.51
    Playing
    0.49
    -playing
    0.47
     Plays
    0.43
    -play
    0.42
    Activations Density 0.124%

    No Known Activations