© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 54491
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "by" indicating authorship or agency

    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
    оÑĢоÑĪ
    -0.13
     opposite
    -0.13
    bish
    -0.12
    аза
    -0.12
    виÑĤ
    -0.12
     bey
    -0.12
    åIJIJ
    -0.11
    веÑĤ
    -0.11
    ::*
    -0.11
    ÌĨ
    -0.11
    POSITIVE LOGITS
     me
    0.20
    :
    0.18
    lined
    0.17
     myself
    0.17
    /on
    0.16
     admin
    0.16
    -election
    0.15
    /from
    0.15
    /about
    0.15
     author
    0.15
    Activations Density 0.166%

    No Known Activations