© 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. 14160
    Prev
    Next
    INDEX
    Explanations

    references to a specific individual and their actions

    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
    UpInside
    -0.15
     hopefully
    -0.14
    eldom
    -0.14
     seldom
    -0.14
    ussen
    -0.13
    ázd
    -0.13
    UFFIX
    -0.13
    egen
    -0.13
    ocrine
    -0.13
    borg
    -0.13
    POSITIVE LOGITS
     actually
    0.68
    actually
    0.55
     actual
    0.49
     Actually
    0.45
    Actually
    0.43
    actual
    0.39
     even
    0.38
     sogar
    0.35
    å®ŀéĻħ
    0.35
     Actual
    0.33
    Activations Density 0.009%

    No Known Activations