© 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. 15803
    Prev
    Next
    INDEX
    Explanations

    phrases related to warnings or advice about safety and caution

    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
    ighbors
    -0.17
    olle
    -0.16
    жд
    -0.15
    hlas
    -0.15
    /umd
    -0.15
    ieri
    -0.15
     hè
    -0.14
    ثار
    -0.14
    ampo
    -0.14
     Bor
    -0.13
    POSITIVE LOGITS
     advice
    0.73
     Advice
    0.60
    Advice
    0.53
     advise
    0.51
     advises
    0.44
     adv
    0.41
     advised
    0.41
     counsel
    0.37
     tips
    0.35
     guidance
    0.35
    Activations Density 0.048%

    No Known Activations