© 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. 14651
    Prev
    Next
    INDEX
    Explanations

    guidelines and precautions related to the safe use of ladders

    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
    âĢ¦the
    -0.15
     middle
    -0.15
     couple
    -0.15
    -0.14
    440
    -0.14
    eka
    -0.14
     side
    -0.14
    âĢ¦and
    -0.13
     inner
    -0.13
    lien
    -0.13
    POSITIVE LOGITS
     venue
    0.22
     venues
    0.19
     premises
    0.18
     Venue
    0.17
    สà¸ĸาà¸Ļà¸Ĺ
    0.17
     environments
    0.17
     surfaces
    0.16
    locations
    0.16
    Locations
    0.15
    -либо
    0.15
    Activations Density 0.187%

    No Known Activations