© 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. 23847
    Prev
    Next
    INDEX
    Explanations

    references to political affiliations and positions

    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
     Labor
    -0.20
     ACLU
    -0.18
     progressive
    -0.17
     Labour
    -0.17
     labor
    -0.16
     Equality
    -0.16
     McG
    -0.16
     Bernie
    -0.15
    alg
    -0.15
    Labor
    -0.15
    POSITIVE LOGITS
     Conserv
    0.32
     conserv
    0.28
     conservatism
    0.27
    Cons
    0.26
    -cons
    0.24
     conservative
    0.23
     conservatives
    0.22
     Conservative
    0.22
     conserve
    0.21
    cons
    0.20
    Activations Density 0.053%

    No Known Activations