© 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. 33021
    Prev
    Next
    INDEX
    Explanations

    terms related to structural elements and visual representations in diagrams or images

    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
    abil
    -0.14
    bara
    -0.14
    zer
    -0.14
    .Side
    -0.13
    ãĥ³ãĥĸ
    -0.12
    ovu
    -0.12
    анÑĸ
    -0.12
    instr
    -0.12
     misunder
    -0.12
    angle
    -0.12
    POSITIVE LOGITS
     upper
    0.41
     bottom
    0.40
     top
    0.38
     middle
    0.37
     center
    0.36
     left
    0.36
    upper
    0.34
     lower
    0.34
    middle
    0.30
     right
    0.30
    Activations Density 0.059%

    No Known Activations