© 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. 41914
    Prev
    Next
    INDEX
    Explanations

    affirmations or agreements in the context of discussions about political or 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
    umba
    -0.17
    elsea
    -0.16
    loth
    -0.16
    yard
    -0.15
    ziel
    -0.15
    acie
    -0.15
    )NULL
    -0.15
    yms
    -0.15
    klad
    -0.14
    tn
    -0.14
    POSITIVE LOGITS
    /no
    0.26
    od
    0.17
    udas
    0.16
    enia
    0.16
    ench
    0.15
    nod
    0.15
    nar
    0.15
    NO
    0.15
     Ter
    0.15
    no
    0.15
    Activations Density 0.005%

    No Known Activations