© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 44950
    Prev
    Next
    INDEX
    Explanations

    numerical values, particularly related to percentages, years, and counts

    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
    qua
    -0.14
    oldur
    -0.14
     RaisePropertyChanged
    -0.14
    _rpc
    -0.14
    ê³¼ìłķ
    -0.13
    ipse
    -0.13
    าะ
    -0.13
    _SELECTOR
    -0.13
    .opendaylight
    -0.13
    ÐĽÐŀ
    -0.13
    POSITIVE LOGITS
    in
    0.15
    ê³
    0.14
    obby
    0.14
    irez
    0.14
     rightly
    0.14
    oulouse
    0.14
    illow
    0.14
    panion
    0.14
    oyer
    0.14
    sp
    0.14
    Activations Density 0.096%

    No Known Activations