© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 54366
    Prev
    Next
    INDEX
    Explanations

    requests for additional information or details

    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
    _HANDLER
    -0.15
    qui
    -0.14
    ius
    -0.14
     knack
    -0.14
    spr
    -0.14
    ntag
    -0.14
    aklı
    -0.13
    idor
    -0.13
    iggins
    -0.13
     extra
    -0.13
    POSITIVE LOGITS
     information
    0.58
     info
    0.48
    information
    0.45
     Information
    0.44
     informatie
    0.41
    ä¿¡æģ¯
    0.41
    Information
    0.40
     información
    0.39
    -information
    0.39
    info
    0.38
    Activations Density 0.037%

    No Known Activations