© 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. 29226
    Prev
    Next
    INDEX
    Explanations

    words related to characters or notable figures in film or entertainment

    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
    icans
    -0.16
    ãĥ¼ãĥ¬
    -0.15
    plain
    -0.15
    stit
    -0.15
    ivos
    -0.14
    asp
    -0.14
    aren
    -0.14
    perc
    -0.14
    borough
    -0.13
    oor
    -0.13
    POSITIVE LOGITS
    naments
    0.17
    aways
    0.17
    away
    0.17
    quoi
    0.16
    ffen
    0.16
    reesome
    0.16
    otropic
    0.15
    erialized
    0.15
    /down
    0.14
    ropic
    0.14
    Activations Density 0.009%

    No Known Activations