© 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. 54932
    Prev
    Next
    INDEX
    Explanations

    end punctuation marks and specific markers indicating structure in the text

    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
     also
    -0.17
    also
    -0.16
    ãĤ
    -0.15
    ãĥ³ãĥĹ
    -0.15
    ëĺIJ
    -0.13
    åīĩ
    -0.13
    later
    -0.13
    @qq
    -0.13
    AllWindows
    -0.13
    edList
    -0.13
    POSITIVE LOGITS
     Indeed
    0.31
    Indeed
    0.29
     indeed
    0.27
    ä¾ĭå¦Ĥ
    0.26
     напÑĢимеÑĢ
    0.26
     witness
    0.25
     According
    0.24
     case
    0.24
     according
    0.24
     napÅĻÃŃklad
    0.24
    Activations Density 0.163%

    No Known Activations