© 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. 29676
    Prev
    Next
    INDEX
    Explanations

    repeated conjunctions

    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
    æĭĽ
    -0.14
     Vz
    -0.13
    omit
    -0.12
    ãĤ¤ãĥ³ãĥĪ
    -0.12
    UBL
    -0.12
    ensa
    -0.12
    ittal
    -0.12
    vara
    -0.12
    âĢį
    -0.12
    pla
    -0.12
    POSITIVE LOGITS
    /or
    0.56
    rogen
    0.31
    rog
    0.30
    /OR
    0.28
    erson
    0.24
    -or
    0.23
    /of
    0.23
    ä¸Ķ
    0.21
    ÑĢониÑĩеÑģ
    0.19
    /o
    0.18
    Activations Density 0.187%

    No Known Activations