© 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. 15632
    Prev
    Next
    INDEX
    Explanations

    descriptions of equipment setup and functionality in a laboratory 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
     Pods
    -0.14
     pods
    -0.14
    宿
    -0.13
    ane
    -0.13
     Fulton
    -0.13
     thân
    -0.13
    orb
    -0.13
     dosy
    -0.13
    hosts
    -0.13
     ØŃض
    -0.13
    POSITIVE LOGITS
     holes
    0.27
     sides
    0.24
     Handles
    0.23
     handles
    0.23
     openings
    0.22
     hole
    0.22
     Hole
    0.21
     lid
    0.20
     doors
    0.19
     walls
    0.19
    Activations Density 0.080%

    No Known Activations