© 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. 24654
    Prev
    Next
    INDEX
    Explanations

    negations and phrases indicating disagreement or dismissal

    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
     any
    -0.18
     XCTAssertTrue
    -0.17
    chn
    -0.15
    ils
    -0.15
    idy
    -0.15
    ita
    -0.15
    cratch
    -0.15
    족
    -0.14
     XCTAssert
    -0.14
    زÙħ
    -0.14
    POSITIVE LOGITS
     exactly
    0.92
     Exactly
    0.72
    Exactly
    0.61
     precisely
    0.51
     exact
    0.44
     Exact
    0.37
     genau
    0.34
    actly
    0.34
    exact
    0.33
    Exact
    0.33
    Activations Density 0.015%

    No Known Activations