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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 30067
    Prev
    Next
    INDEX
    Explanations

    references to men and men's issues

    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
    piring
    -0.16
    erc
    -0.15
    ighton
    -0.15
    g
    -0.15
    er
    -0.15
    ãĥĭãĤ¢
    -0.15
    atre
    -0.15
    uze
    -0.14
    (es
    -0.14
     FactoryBot
    -0.14
    POSITIVE LOGITS
    opause
    0.33
    aced
    0.30
    ial
    0.30
    aces
    0.28
    hir
    0.26
    iscal
    0.25
    acing
    0.25
    ager
    0.24
    ubar
    0.24
    ards
    0.23
    Activations Density 0.015%

    No Known Activations