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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 23613
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter 'R'

    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
    oy
    -0.19
    аз
    -0.18
    าย
    -0.17
    ад
    -0.16
    io
    -0.16
    ãĤŃãĥ¥
    -0.15
    XS
    -0.15
    az
    -0.15
    eph
    -0.15
    entiful
    -0.15
    POSITIVE LOGITS
    alent
    0.17
    .styleable
    0.16
    rans
    0.16
    arus
    0.15
    ATHER
    0.15
    malink
    0.15
    .drawable
    0.15
    ur
    0.15
     elig
    0.15
    /place
    0.15
    Activations Density 0.034%

    No Known Activations