© 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. 21433
    Prev
    Next
    INDEX
    Explanations

    terms related to complex political and social issues

    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
    affle
    -0.15
    umption
    -0.15
    igsaw
    -0.14
    quisition
    -0.14
    .examples
    -0.14
    pline
    -0.14
    nergie
    -0.14
    parer
    -0.14
    aviest
    -0.14
    udge
    -0.13
    POSITIVE LOGITS
    etheless
    0.29
    uably
    0.23
    ally
    0.22
    theless
    0.20
    ificantly
    0.19
    oubtedly
    0.19
    sequently
    0.19
    prisingly
    0.18
    ably
    0.18
    unately
    0.18
    Activations Density 0.942%

    No Known Activations