© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 9000
    Prev
    Next
    INDEX
    Explanations

    expressions of enthusiasm or support for artistic endeavors

    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
    imli
    -0.17
    ellido
    -0.15
     ðŁĺī↵↵
    -0.15
    ostel
    -0.15
    ấn
    -0.15
    请éĢīæĭ©
    -0.14
     LOL
    -0.14
    Boy
    -0.13
    laughs
    -0.13
     yerinde
    -0.13
    POSITIVE LOGITS
    duto
    0.18
    edit
    0.15
     Hope
    0.15
     x
    0.15
     prec
    0.15
    owo
    0.14
    ìļ´ëį°
    0.14
     hope
    0.14
     lem
    0.14
    !
    0.14
    Activations Density 0.027%

    No Known Activations