© 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. 30191
    Prev
    Next
    INDEX
    Explanations

    expressions of personal opinions or feelings

    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
     Fear
    -0.16
     fear
    -0.15
    Fear
    -0.15
    apo
    -0.15
     have
    -0.15
    .dataTables
    -0.14
    ãģ¡ãĤĥãĤĵ
    -0.14
    çī¹èī²
    -0.14
    ç²Ĵ
    -0.14
    .opend
    -0.14
    POSITIVE LOGITS
     preference
    0.30
     preferences
    0.29
     Prefer
    0.28
     prefer
    0.28
     Preference
    0.27
     prefers
    0.26
    prefer
    0.25
    Preference
    0.24
     Preferences
    0.23
     preferred
    0.21
    Activations Density 0.010%

    No Known Activations