© 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. 8934
    Prev
    Next
    INDEX
    Explanations

    references to remote-controlled personal items or novelty gadgets

    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
     gest
    -0.17
    ifax
    -0.15
    TRACT
    -0.15
    RunLoop
    -0.15
     Germ
    -0.15
    agi
    -0.15
     irresistible
    -0.14
    oday
    -0.14
    DCF
    -0.14
    iese
    -0.14
    POSITIVE LOGITS
     toy
    0.30
     toys
    0.30
     Toys
    0.27
    Toy
    0.23
     pleasure
    0.23
    toy
    0.23
     Toy
    0.23
     Ple
    0.22
     vibr
    0.22
     Vibr
    0.20
    Activations Density 0.021%

    No Known Activations