© 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. 33018
    Prev
    Next
    INDEX
    Explanations

    expressions indicating states or conditions

    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
     finally
    -0.20
    finally
    -0.18
     Finally
    -0.17
    'gc
    -0.16
    acier
    -0.14
    Finally
    -0.14
     periodically
    -0.14
    ombat
    -0.14
    ideon
    -0.14
    lassian
    -0.14
    POSITIVE LOGITS
     immediate
    0.95
     immediately
    0.93
     immedi
    0.73
     instantly
    0.72
     Immediate
    0.71
     instant
    0.68
     sofort
    0.67
     quickly
    0.66
     Immediately
    0.65
     quick
    0.61
    Activations Density 0.019%

    No Known Activations