© 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. 15618
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly quotation marks and apostrophes

    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
    $MESS
    -0.18
    {}]
    -0.16
    atre
    -0.16
    {}.
    -0.16
    <
    -0.16
    #{
    -0.15
    mps
    -0.14
    {}'.
    -0.14
    versed
    -0.14
    igy
    -0.14
    POSITIVE LOGITS
    s
    0.22
    :",
    0.17
    jure
    0.16
    ..."↵
    0.15
    ford
    0.15
    atter
    0.15
    .*
    0.14
    %%
    0.14
    fort
    0.14
    ..."
    0.14
    Activations Density 0.029%

    No Known Activations