© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 41616
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals and their actions or states

    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
    terdam
    -0.15
     wonder
    -0.14
    itsu
    -0.14
    463
    -0.14
    _Api
    -0.14
     wondered
    -0.14
    eya
    -0.14
    á»§i
    -0.13
    ainless
    -0.13
    isque
    -0.13
    POSITIVE LOGITS
    ark
    0.25
    aves
    0.21
     later
    0.16
     partially
    0.15
     term
    0.15
    uje
    0.15
    .AttributeSet
    0.15
    uj
    0.15
     described
    0.15
    pins
    0.15
    Activations Density 0.059%

    No Known Activations