© 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. 63409
    Prev
    Next
    INDEX
    Explanations

    narratives of personal struggles with guilt and confusion

    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
     tomorrow
    -0.17
     Tomorrow
    -0.17
     predecess
    -0.16
    Tomorrow
    -0.16
     hopefully
    -0.15
    longleftrightarrow
    -0.15
     currently
    -0.15
     retiring
    -0.14
    Earlier
    -0.14
    Minutes
    -0.14
    POSITIVE LOGITS
     eventually
    0.28
     Eventually
    0.27
    Eventually
    0.25
     eventual
    0.23
     month
    0.20
     months
    0.18
     those
    0.17
     soon
    0.16
     finally
    0.15
     Month
    0.15
    Activations Density 0.014%

    No Known Activations