© 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. 29492
    Prev
    Next
    INDEX
    Explanations

    key terms associated with significant changes or events in market activity

    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
    cts
    -0.17
     screams
    -0.16
    utschein
    -0.15
    Contours
    -0.14
    uento
    -0.14
    ÑĥÑħ
    -0.14
    isto
    -0.14
    egers
    -0.14
    otec
    -0.14
    (crate
    -0.14
    POSITIVE LOGITS
     terror
    0.33
     terr
    0.27
     shock
    0.26
     surprise
    0.25
     catch
    0.24
     catching
    0.24
     mort
    0.23
     baff
    0.23
     awe
    0.22
     fasc
    0.22
    Activations Density 0.033%

    No Known Activations