© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 43294
    Prev
    Next
    INDEX
    Explanations

    references to durations of time, particularly weeks and months

    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
    ils
    -0.16
    793
    -0.15
    à¸Ĥว
    -0.15
    ids
    -0.15
    oad
    -0.14
    ability
    -0.14
    RuleContext
    -0.14
    uto
    -0.14
    ais
    -0.14
    ourg
    -0.14
    POSITIVE LOGITS
     worth
    0.55
     Worth
    0.40
    worth
    0.38
    sworth
    0.24
     worthy
    0.22
     worthwhile
    0.19
    worthy
    0.18
     entirety
    0.18
     supply
    0.17
    quo
    0.17
    Activations Density 0.030%

    No Known Activations