© 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. 14813
    Prev
    Next
    INDEX
    Explanations

    instances of the word "may."

    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
    ophon
    -0.17
    _sequences
    -0.14
    UTION
    -0.14
    scene
    -0.14
    scenes
    -0.14
    ference
    -0.14
    umba
    -0.13
    cent
    -0.13
    raq
    -0.13
    rez
    -0.12
    POSITIVE LOGITS
    \views
    0.16
    าศ
    0.15
    zing
    0.15
    unar
    0.15
    Boolean
    0.15
    OperationException
    0.15
     skoro
    0.14
     INCIDENT
    0.14
    ΡÎĻ
    0.14
    FIELDS
    0.13
    Activations Density 0.001%

    No Known Activations