© 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. 54427
    Prev
    Next
    INDEX
    Explanations

    instances of assessment or commentary about situations and attitudes

    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
    vana
    -0.15
    IDDEN
    -0.14
     cui
    -0.14
    ieder
    -0.13
     meno
    -0.12
     underlying
    -0.12
    CLUDED
    -0.12
     fate
    -0.12
    okane
    -0.12
    овеÑĢ
    -0.12
    POSITIVE LOGITS
     ones
    0.43
     one
    0.35
     eines
    0.24
     quello
    0.22
     Ones
    0.21
     bahwa
    0.21
     ÙĪاØŃدة
    0.21
     celui
    0.21
    ones
    0.21
     that
    0.20
    Activations Density 0.108%

    No Known Activations