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. 41375
    Prev
    Next
    INDEX
    Explanations

    terms related to editing and editing tools

    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
    олеÑĤ
    -0.16
    /errors
    -0.16
    ongs
    -0.15
    acha
    -0.15
    holds
    -0.14
    ạng
    -0.14
    meld
    -0.14
    imum
    -0.14
     Yön
    -0.14
    PARAM
    -0.14
    POSITIVE LOGITS
    ials
    0.24
    ting
    0.21
    /view
    0.20
    ied
    0.19
    ì¦Ŀ
    0.17
    .au
    0.17
    monds
    0.16
    ors
    0.16
    ship
    0.16
    rix
    0.16
    Activations Density 0.019%

    No Known Activations