© 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. 9084
    Prev
    Next
    INDEX
    Explanations

    punctuation and sentence-ending markers

    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
     it
    -0.31
    å®ĥ
    -0.30
    It
    -0.24
     воно
    -0.23
     оно
    -0.23
    -it
    -0.22
     its
    -0.22
     It
    -0.20
    	It
    -0.19
    _it
    -0.19
    POSITIVE LOGITS
     the
    0.18
     portions
    0.16
     The
    0.15
    Fcn
    0.14
    peq
    0.14
    ucha
    0.14
    лим
    0.14
    âĢ¦the
    0.13
    anken
    0.13
    Cop
    0.13
    Activations Density 0.028%

    No Known Activations