© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 14419
    Prev
    Next
    INDEX
    Explanations

    phrases indicating actions or transitions

    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
    rippling
    -0.14
    á»ĥm
    -0.14
    ToEnd
    -0.14
    UIL
    -0.14
    éĻ
    -0.14
    overy
    -0.14
     sighting
    -0.14
    isable
    -0.13
    ZN
    -0.13
    IGHL
    -0.13
    POSITIVE LOGITS
    /from
    0.28
     match
    0.22
     be
    0.21
     nearest
    0.19
    ogle
    0.19
    gether
    0.19
     another
    0.19
     a
    0.19
     avoid
    0.18
     its
    0.18
    Activations Density 0.124%

    No Known Activations