Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 15922
    Prev
    Next
    INDEX
    Explanations

    statements related to claims, statistics, and projections

    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
     maybe
    -0.30
     perhaps
    -0.28
     possibly
    -0.27
     apparently
    -0.27
     seemingly
    -0.26
     Maybe
    -0.26
    maybe
    -0.26
    Maybe
    -0.26
     vielleicht
    -0.24
     Apparently
    -0.23
    POSITIVE LOGITS
     somewhere
    0.19
     plenty
    0.18
     many
    0.18
     similarly
    0.17
     bastante
    0.17
     already
    0.16
    GD
    0.15
    many
    0.15
     alguna
    0.15
    ibbon
    0.15
    Activations Density 0.072%

    No Known Activations