© 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 EvalsExportsinterp-engineNEWAPI 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. 43567
    Prev
    Next
    INDEX
    Explanations

    expressions of intention or desire related to discourse and recommendations

    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
    PTY
    -0.15
     Plantae
    -0.13
    ublik
    -0.13
     resignation
    -0.13
    amet
    -0.13
    oupon
    -0.12
    วย
    -0.12
    ierarchy
    -0.12
    phia
    -0.12
    reshold
    -0.12
    POSITIVE LOGITS
     vintage
    0.62
     retro
    0.58
     Vintage
    0.56
     historical
    0.54
    Vintage
    0.53
     Retro
    0.51
     nostalgic
    0.49
     historic
    0.47
     Historical
    0.47
     antique
    0.46
    Activations Density 0.016%

    No Known Activations