© 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. 54251
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate quantity or degree of importance

    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
    667
    -0.16
    æĮ¯ãĤĬ
    -0.15
    PathParam
    -0.15
    omy
    -0.14
    ãģ¨ãģĵãĤį
    -0.14
    venient
    -0.14
    NotFoundError
    -0.13
    rub
    -0.13
    à¥įरपत
    -0.13
    aku
    -0.13
    POSITIVE LOGITS
     reason
    1.32
     reasons
    1.25
    reason
    1.08
     Reasons
    1.03
    Reason
    1.02
     Reason
    1.00
    _reason
    0.85
    .reason
    0.83
    åİŁåĽł
    0.78
    çIJĨçĶ±
    0.76
    Activations Density 0.058%

    No Known Activations