© 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. 22513
    Prev
    Next
    INDEX
    Explanations

    instances of political deception and hidden agendas

    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
    _RESERVED
    -0.16
    itom
    -0.15
    ilty
    -0.14
    unca
    -0.14
    icom
    -0.13
    legate
    -0.13
     pudd
    -0.13
     zobraz
    -0.12
    лÑĸд
    -0.12
     lett
    -0.12
    POSITIVE LOGITS
     mask
    0.60
     masks
    0.54
    mask
    0.54
     Mask
    0.53
    Mask
    0.50
     masking
    0.49
     disguise
    0.49
    -mask
    0.48
     cover
    0.48
     MASK
    0.46
    Activations Density 0.050%

    No Known Activations