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. 23743
    Prev
    Next
    INDEX
    Explanations

    references to forensic methods and their scrutiny

    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
    ợ
    -0.15
    _MONITOR
    -0.15
    adero
    -0.14
    eming
    -0.14
     scouting
    -0.14
    throat
    -0.14
     vess
    -0.14
    eggies
    -0.14
     addCriterion
    -0.13
    rise
    -0.13
    POSITIVE LOGITS
     fore
    0.71
     Fore
    0.68
    Fore
    0.61
    fore
    0.58
     FORE
    0.52
     forensic
    0.51
    _fore
    0.43
    .fore
    0.42
    FORE
    0.38
     crime
    0.34
    Activations Density 0.051%

    No Known Activations