© 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. 41799
    Prev
    Next
    INDEX
    Explanations

    phrases related to evidence and specifics in an investigation context

    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
     Torch
    -0.16
    ยà¸ģ
    -0.15
    torch
    -0.15
     oils
    -0.15
     torch
    -0.14
     bombed
    -0.14
     bombing
    -0.14
    529
    -0.14
     Bom
    -0.14
     Hamp
    -0.14
    POSITIVE LOGITS
     bullet
    0.52
     bullets
    0.45
    bullet
    0.44
     Bullet
    0.41
    Bullet
    0.39
     Bul
    0.33
     rounds
    0.33
    _bullet
    0.31
    bul
    0.30
     Rounds
    0.28
    Activations Density 0.041%

    No Known Activations