© 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. 54883
    Prev
    Next
    INDEX
    Explanations

    descriptors of appearance, particularly related to clothing and accessories

    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
    ieri
    -0.15
    çļ®
    -0.14
    skin
    -0.14
    iqu
    -0.14
     Skin
    -0.14
    ukkit
    -0.14
    à¹Ģà¸ŀล
    -0.13
    urre
    -0.13
     skin
    -0.13
    ertz
    -0.13
    POSITIVE LOGITS
     glasses
    0.59
     spect
    0.56
     Glasses
    0.49
     sunglasses
    0.44
     Spect
    0.42
    spect
    0.40
     spectacle
    0.40
    lasses
    0.39
     ey
    0.36
     specs
    0.35
    Activations Density 0.025%

    No Known Activations