© 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. 41992
    Prev
    Next
    INDEX
    Explanations

    terms related to sports injuries

    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
     ÑģоÑģÑĤ
    -0.16
    _echo
    -0.15
    .RunWith
    -0.14
    coe
    -0.14
    ï½Ĵ
    -0.14
    樹
    -0.14
     Ris
    -0.14
    &o
    -0.14
    roe
    -0.14
    vice
    -0.14
    POSITIVE LOGITS
     injury
    0.44
     Injury
    0.37
     injuries
    0.35
     injured
    0.31
     inj
    0.28
     injuring
    0.26
     season
    0.24
    juries
    0.22
     serious
    0.21
     ACL
    0.21
    Activations Density 0.036%

    No Known Activations