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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 15821
    Prev
    Next
    INDEX
    Explanations

    discussions about the significance of minority groups in the context of electoral politics

    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
    irmed
    -0.15
    akening
    -0.14
    ucid
    -0.14
    iaux
    -0.14
    uzey
    -0.14
    udio
    -0.13
    agar
    -0.13
    çĤī
    -0.13
    roma
    -0.13
    gnu
    -0.13
    POSITIVE LOGITS
     dispro
    0.42
     Pro
    0.38
    pro
    0.38
     disproportionate
    0.34
     proport
    0.34
     prop
    0.34
     proportion
    0.33
    Pro
    0.33
     pro
    0.31
     propor
    0.31
    Activations Density 0.070%

    No Known Activations