© 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. 25598
    Prev
    Next
    INDEX
    Explanations

    expressions related to artistic collaboration and creativity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words and phrases related to artistic or creative endeavors.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @aml7990
    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
    Ìĥ
    -0.17
    inea
    -0.17
    esi
    -0.15
    ิà¹Ĥà¸Ļ
    -0.15
    illac
    -0.15
     Tail
    -0.14
    _tail
    -0.14
    orie
    -0.14
    isan
    -0.14
    ấp
    -0.13
    POSITIVE LOGITS
     vision
    0.21
     sens
    0.20
     touch
    0.20
     genius
    0.19
     output
    0.18
     expression
    0.18
     instincts
    0.18
     latitude
    0.18
     direction
    0.17
     voice
    0.17
    Activations Density 0.073%

    No Known Activations