© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 55244
    Prev
    Next
    INDEX
    Explanations

    terms related to assessments or evaluations of situations and people

    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
    cape
    -0.18
    Ùĩ
    -0.17
    (Keys
    -0.16
    न
    -0.16
    ucc
    -0.16
    pace
    -0.15
    StandardItem
    -0.15
    .Classes
    -0.15
    mie
    -0.15
    creen
    -0.15
    POSITIVE LOGITS
    们
    0.57
    åĢij
    0.48
    (s
    0.46
    sWith
    0.43
    swith
    0.41
    ings
    0.41
    ss
    0.41
    es
    0.41
    [s
    0.40
    ies
    0.39
    Activations Density 0.034%

    No Known Activations