© 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. 9110
    Prev
    Next
    INDEX
    Explanations

    instances of the word "post" in various forms

    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
    usat
    -0.18
    vÃŃ
    -0.17
    zelf
    -0.16
     phải
    -0.14
     priesthood
    -0.14
    rer
    -0.14
    usp
    -0.14
    antes
    -0.14
    apter
    -0.14
    fast
    -0.14
    POSITIVE LOGITS
    ulate
    0.35
    pone
    0.31
    graduate
    0.30
    erior
    0.30
    natal
    0.28
    greSQL
    0.28
    ulates
    0.27
    ulated
    0.27
    uring
    0.25
    ures
    0.24
    Activations Density 0.034%

    No Known Activations