© 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. 29078
    Prev
    Next
    INDEX
    Explanations

    references to specific nationalities and possessive forms

    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
     kingdoms
    -0.13
    èµĸ
    -0.13
     .↵↵
    -0.12
     libertin
    -0.12
    ICollection
    -0.12
     fleeting
    -0.12
    âĢ¢
    -0.11
     thrilling
    -0.11
    —
    -0.11
     [↵↵
    -0.11
    POSITIVE LOGITS
     инÑĦоÑĢма
    0.17
     stuff
    0.15
     докÑĥм
    0.14
     effort
    0.14
    ëį°ìĿ´íĬ¸
    0.14
    orsi
    0.14
    cilik
    0.14
     ÑģпÑĢави
    0.14
    ehler
    0.13
    plx
    0.13
    Activations Density 0.001%

    No Known Activations