© 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. 41763
    Prev
    Next
    INDEX
    Explanations

    phrases indicating extreme negativity towards specific dog breeds

    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
    avenport
    -0.16
    надлеж
    -0.15
    ANCH
    -0.15
    üst
    -0.15
    anch
    -0.15
    æīĭãĤĴ
    -0.14
    ney
    -0.14
    лин
    -0.14
    NEY
    -0.14
    yah
    -0.14
    POSITIVE LOGITS
     margin
    0.36
     margins
    0.35
     Margin
    0.28
    margin
    0.28
     factor
    0.27
    Margins
    0.26
     marg
    0.26
     wide
    0.26
     Marg
    0.25
     factors
    0.23
    Activations Density 0.027%

    No Known Activations