© 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
    3. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 24332
    Prev
    Next
    INDEX
    Explanations

    phrases related to judgment and evaluation criteria

    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
     actionTypes
    -0.15
     sä
    -0.14
    zsche
    -0.14
    edium
    -0.14
    ulumi
    -0.14
    /Dk
    -0.14
    æĬŀ
    -0.14
    adium
    -0.14
    Įĵ
    -0.14
    },'
    -0.14
    POSITIVE LOGITS
     factors
    0.34
     whether
    0.32
     how
    0.30
     criteria
    0.30
     merit
    0.26
     Factors
    0.25
     factor
    0.24
    criteria
    0.24
    whether
    0.23
     their
    0.23
    Activations Density 0.095%

    No Known Activations