© 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. 29008
    Prev
    Next
    INDEX
    Explanations

    various forms of punctuation and expressive language elements, indicating strong emotional reactions or frustrations

    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
     articles
    -0.18
     news
    -0.17
     article
    -0.17
     coverage
    -0.17
     Reuters
    -0.16
    ICY
    -0.16
     News
    -0.15
     ARTICLE
    -0.14
    -news
    -0.14
    Article
    -0.14
    POSITIVE LOGITS
    end
    0.16
    eof
    0.16
    /end
    0.16
     END
    0.16
    -cols
    0.15
    isposable
    0.15
    blr
    0.15
    edback
    0.15
     życ
    0.14
     @}
    0.14
    Activations Density 0.041%

    No Known Activations