Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 23240
    Prev
    Next
    INDEX
    Explanations

    references to functions or concepts related to "fun" or structured processes (like funnels) in various contexts

    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
    een
    -0.19
    anford
    -0.16
     Armour
    -0.16
    theless
    -0.16
    pery
    -0.16
    gang
    -0.15
    rias
    -0.15
    AGE
    -0.15
    leck
    -0.15
    оÑĤÑĢеб
    -0.15
    POSITIVE LOGITS
    erals
    0.34
    tion
    0.30
    nels
    0.29
    nel
    0.28
    ctors
    0.28
    eral
    0.25
    ereal
    0.25
    amental
    0.25
    zione
    0.24
    ctor
    0.23
    Activations Density 0.012%

    No Known Activations