© 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. 54379
    Prev
    Next
    INDEX
    Explanations

    references to prophesies and their implications in a political context

    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
    rowable
    -0.16
    egov
    -0.16
    hiba
    -0.14
    _losses
    -0.14
    اÙĨس
    -0.14
    inne
    -0.14
     shrine
    -0.14
     Shrine
    -0.14
    Ïģιά
    -0.14
    plr
    -0.14
    POSITIVE LOGITS
     fulfillment
    0.23
     Arm
    0.23
     Judgment
    0.22
     End
    0.22
     prop
    0.22
     judgment
    0.21
     fulfill
    0.21
     fulfilled
    0.20
    Arm
    0.20
     end
    0.20
    Activations Density 0.030%

    No Known Activations