© 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. 9114
    Prev
    Next
    INDEX
    Explanations

    mentions of certain individuals or entities related to political influence and corruption

    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
    lady
    -0.14
    anken
    -0.14
     Legend
    -0.14
    riad
    -0.14
    Ke
    -0.14
    ystone
    -0.14
    reh
    -0.13
    atedRoute
    -0.13
    @register
    -0.13
    éĢ¸
    -0.13
    POSITIVE LOGITS
    uma
    0.17
    exit
    0.17
    byn
    0.16
     vej
    0.16
    amb
    0.15
    ulu
    0.15
    ambia
    0.15
    ávÄĽ
    0.14
     African
    0.14
    aire
    0.14
    Activations Density 0.004%

    No Known Activations