© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 15155
    Prev
    Next
    INDEX
    Explanations

    instances of specific physical actions related to throwing and shooting

    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
    alet
    -0.14
    illion
    -0.13
    ród
    -0.13
     ISA
    -0.13
    undred
    -0.13
    wd
    -0.13
    edd
    -0.13
     Tet
    -0.13
     Forum
    -0.13
     Rin
    -0.13
    POSITIVE LOGITS
     throw
    1.34
     Throw
    1.23
    throw
    1.22
     throwing
    1.19
     thrown
    1.18
    Throw
    1.18
     throws
    1.16
     THROW
    1.10
     threw
    1.10
     toss
    0.99
    Activations Density 0.026%

    No Known Activations