© 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. 63518
    Prev
    Next
    INDEX
    Explanations

    references to tools, concepts, and tactics related to media and information dissemination

    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
    andin
    -0.15
    /animations
    -0.14
    otate
    -0.13
    eki
    -0.13
    лей
    -0.13
    ccione
    -0.12
    лÑıн
    -0.12
    FieldValue
    -0.12
     those
    -0.12
    lew
    -0.12
    POSITIVE LOGITS
     called
    0.96
    called
    0.80
     Called
    0.75
    åı«
    0.65
    Called
    0.64
     known
    0.61
     llam
    0.58
     named
    0.57
    -called
    0.55
    known
    0.53
    Activations Density 0.140%

    No Known Activations