© 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. 29118
    Prev
    Next
    INDEX
    Explanations

    statements regarding the dispelling of rumors and clarifications from companies

    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
    коз
    -0.14
    compact
    -0.14
     tavs
    -0.14
    ges
    -0.14
     pulumi
    -0.14
    ErrorException
    -0.14
    ups
    -0.14
     Barbar
    -0.14
    à¥įपन
    -0.13
    æk
    -0.13
    POSITIVE LOGITS
     disp
    0.58
     Disp
    0.48
    disp
    0.47
    Disp
    0.44
     dispersion
    0.38
     bust
    0.35
     DISP
    0.33
     dispens
    0.32
     clearing
    0.30
     qu
    0.30
    Activations Density 0.055%

    No Known Activations