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. 9348
    Prev
    Next
    INDEX
    Explanations

    references to vehicle descriptions and license plates

    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
    .Reporting
    -0.15
    edin
    -0.13
    ẻ
    -0.13
     Gaut
    -0.13
    rado
    -0.13
    flt
    -0.13
    Ãħ
    -0.12
    ãĤ£
    -0.12
    iferay
    -0.12
     prz
    -0.12
    POSITIVE LOGITS
    yte
    0.14
    igue
    0.13
    perty
    0.13
    aler
    0.13
    alers
    0.13
    532
    0.13
    _Tis
    0.13
    351
    0.13
    ience
    0.12
    ignKey
    0.12
    Activations Density 0.326%

    No Known Activations