© 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. 41651
    Prev
    Next
    INDEX
    Explanations

    keywords related to economic transactions and consumer activity

    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
    ."↵↵↵
    -0.15
    asher
    -0.14
    ï¼īãĢĤ↵↵
    -0.13
    ).↵↵
    -0.13
    ").↵↵
    -0.13
    .”↵↵
    -0.13
    ãĢĤãĢį↵↵
    -0.13
    _$_
    -0.13
    ”.↵↵
    -0.13
     aforementioned
    -0.12
    POSITIVE LOGITS
     |
    0.23
     ####
    0.21
     ###
    0.19
     #####
    0.19
     ##
    0.17
    ÑĢаÐ
    0.17
    ă
    0.17
    ↵
    0.17
    <br
    0.16
    ":
    0.16
    Activations Density 0.356%

    No Known Activations