© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 43454
    Prev
    Next
    INDEX
    Explanations

    mention of ideas and proposals, particularly in the context of contests or pitches for funding

    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
    лÑĥг
    -0.16
    -uppercase
    -0.16
    arih
    -0.15
    åº
    -0.15
    glich
    -0.14
    arel
    -0.14
     responseObject
    -0.14
     ########.
    -0.13
    .monitor
    -0.13
    .setAction
    -0.13
    POSITIVE LOGITS
     pitch
    0.69
    pitch
    0.61
     Pitch
    0.60
    Pitch
    0.59
     pitching
    0.57
     pitches
    0.57
     pitched
    0.51
    _pitch
    0.45
    .pitch
    0.44
     presentation
    0.39
    Activations Density 0.023%

    No Known Activations