© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 42225
    Prev
    Next
    INDEX
    Explanations

    details related to data segmentation and granularity in analyses

    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
    rost
    -0.17
     Cole
    -0.14
     Mour
    -0.13
    ÙĪÛĮÙĦ
    -0.13
     proper
    -0.13
    .Startup
    -0.13
    NaN
    -0.13
     Cop
    -0.13
    ÅĻi
    -0.13
    _stand
    -0.13
    POSITIVE LOGITS
     gran
    0.41
     detail
    0.38
     fine
    0.37
     granularity
    0.37
    gran
    0.36
    fine
    0.36
    Fine
    0.35
     Gran
    0.34
     Fine
    0.34
    Gran
    0.33
    Activations Density 0.036%

    No Known Activations