© 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. 15621
    Prev
    Next
    INDEX
    Explanations

    occurrences of the abbreviation "OR" or related terms indicating options or alternatives

    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
    ively
    -0.17
    edly
    -0.17
    ey
    -0.17
    ility
    -0.17
    tera
    -0.15
    agers
    -0.15
    że
    -0.15
    igua
    -0.15
    emas
    -0.14
    indre
    -0.14
    POSITIVE LOGITS
    ourke
    0.26
    ignal
    0.26
    ifice
    0.24
    acular
    0.23
    iginal
    0.23
     else
    0.22
    tega
    0.22
    ogonal
    0.21
    ANGE
    0.20
    ients
    0.20
    Activations Density 0.041%

    No Known Activations