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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 15068
    Prev
    Next
    INDEX
    Explanations

    references to time and sequences of events

    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
    füh
    -0.17
    onet
    -0.17
    ModifiedDate
    -0.17
    TOTYPE
    -0.16
    ixel
    -0.15
    aday
    -0.15
    ozem
    -0.15
    emachine
    -0.15
    angible
    -0.15
    @show
    -0.14
    POSITIVE LOGITS
     span
    0.81
    span
    0.55
     space
    0.53
     spans
    0.53
    Span
    0.53
    -span
    0.52
     Span
    0.50
     Space
    0.42
    Space
    0.41
     matter
    0.41
    Activations Density 0.024%

    No Known Activations