© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 29282
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures and partisan affiliations

    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
    antine
    -0.17
    éĢģæĸĻçĦ¡æĸĻ
    -0.16
    ŀ
    -0.16
     Vys
    -0.15
    ãĥ¼ãĥľ
    -0.14
    stag
    -0.14
    LBL
    -0.14
     Všech
    -0.14
    ä¹ħ
    -0.14
    ramework
    -0.14
    POSITIVE LOGITS
     Donald
    0.56
     Trump
    0.49
    Donald
    0.46
    Trump
    0.42
    -Trump
    0.33
     trump
    0.32
    realDonaldTrump
    0.30
    onald
    0.25
    DonaldTrump
    0.24
     President
    0.24
    Activations Density 0.202%

    No Known Activations