© 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. 30077
    Prev
    Next
    INDEX
    Explanations

    first-person expressions of personal experience and opinion

    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
    ylland
    -0.17
    ÑĤÑİ
    -0.17
     Dün
    -0.14
    ror
    -0.14
    $MESS
    -0.14
    zik
    -0.13
    agini
    -0.13
     ()->
    -0.13
    $LANG
    -0.13
    ÌĨ
    -0.13
    POSITIVE LOGITS
     couldn
    0.48
     cannot
    0.42
     Couldn
    0.40
    couldn
    0.39
     cant
    0.37
    Couldn
    0.36
    cannot
    0.35
     Cannot
    0.35
    Cannot
    0.34
     unable
    0.34
    Activations Density 0.013%

    No Known Activations