© 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. 44889
    Prev
    Next
    INDEX
    Explanations

    negative constructions about freedom or constraints

    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
    ÑĢÑıд
    -0.14
    olin
    -0.14
     Anything
    -0.14
     Woodward
    -0.14
    iller
    -0.14
    Ł
    -0.13
    ett
    -0.13
    eware
    -0.13
     Fischer
    -0.13
    æļ
    -0.13
    POSITIVE LOGITS
     completely
    0.81
     entirely
    0.67
     Completely
    0.65
     totally
    0.63
    å®Įåħ¨
    0.57
     completamente
    0.50
     altogether
    0.48
     complete
    0.48
     COMPLETE
    0.48
     Totally
    0.46
    Activations Density 0.038%

    No Known Activations