© 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. 32915
    Prev
    Next
    INDEX
    Explanations

    terms related to speculation and speculative activities

    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
    olan
    -0.17
    -blood
    -0.16
    entifier
    -0.15
    imizer
    -0.15
    reen
    -0.15
    een
    -0.14
     respective
    -0.14
    roll
    -0.14
    죽
    -0.14
    кÑĥлÑĮ
    -0.14
    POSITIVE LOGITS
    ulative
    0.18
    imens
    0.17
    /spec
    0.17
    ãĥ¥
    0.17
    acular
    0.15
    281
    0.15
    à¸ģารà¸ĵ
    0.15
    a
    0.15
    oeff
    0.15
    (spec
    0.15
    Activations Density 0.016%

    No Known Activations