© 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. 29739
    Prev
    Next
    INDEX
    Explanations

    references to film and cinema-related examples, particularly focusing on notable directors and films

    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
    stad
    -0.14
    ,");↵
    -0.13
    acco
    -0.13
    eer
    -0.12
    ushima
    -0.12
    دÙĪ
    -0.12
    InThe
    -0.12
     '),
    -0.11
     zx
    -0.11
    (_)
    -0.11
    POSITIVE LOGITS
    ↵↵
    0.27
    ;
    0.24
    )↵↵
    0.23
    )↵
    0.23
    ;↵
    0.22
    ↵
    0.22
     -
    0.22
     (
    0.21
    ;↵↵
    0.19
    ]↵↵
    0.18
    Activations Density 0.785%

    No Known Activations