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. 15915
    Prev
    Next
    INDEX
    Explanations

    references to the character "Vertigo" in relation to a superhero context

    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
    rious
    -0.16
    dbus
    -0.15
    haf
    -0.15
    umping
    -0.15
    .Solid
    -0.15
    athing
    -0.15
    entiful
    -0.14
     plá
    -0.14
     Banc
    -0.14
     Bac
    -0.14
    POSITIVE LOGITS
    ebra
    0.38
    igo
    0.29
    igin
    0.23
    brate
    0.22
    bral
    0.21
    ically
    0.21
    icle
    0.21
    umn
    0.20
    IGO
    0.20
    ommen
    0.20
    Activations Density 0.005%

    No Known Activations