© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 63337
    Prev
    Next
    INDEX
    Explanations

    references to generic objects or concepts

    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
    quin
    -0.16
     Fucking
    -0.16
    ogne
    -0.16
    ë¶ĢíĦ°
    -0.16
    foundland
    -0.15
    bsolute
    -0.15
    ymous
    -0.14
    udes
    -0.14
    ansom
    -0.14
    лиÑĩ
    -0.14
    POSITIVE LOGITS
    s
    0.40
    sburg
    0.22
    Ùĩ
    0.22
    iness
    0.20
    न
    0.20
    ings
    0.19
    sian
    0.19
    y
    0.19
    sak
    0.18
    INGS
    0.18
    Activations Density 0.025%

    No Known Activations