© 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. 33082
    Prev
    Next
    INDEX
    Explanations

    references to notable voice actors and their roles

    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
    oller
    -0.15
    abort
    -0.14
     aest
    -0.13
     tune
    -0.13
    olet
    -0.13
    ä¸ĬãģĮ
    -0.13
    979
    -0.13
    uC
    -0.13
    γÏĮ
    -0.13
     Tune
    -0.13
    POSITIVE LOGITS
     voice
    0.67
     Voice
    0.57
     voices
    0.56
    voice
    0.54
     vo
    0.54
    Voice
    0.49
     voiced
    0.48
     Voices
    0.47
    vo
    0.44
    voices
    0.43
    Activations Density 0.052%

    No Known Activations