© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 43233
    Prev
    Next
    INDEX
    Explanations

    references to cinematic shots or photography

    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
    ehir
    -0.19
    sen
    -0.19
    hal
    -0.18
    hill
    -0.18
    hall
    -0.17
    oÄŁ
    -0.17
    AndPassword
    -0.17
    ร
    -0.16
    oit
    -0.16
    íĥ
    -0.16
    POSITIVE LOGITS
    guns
    0.34
    ting
    0.32
    tery
    0.24
    ter
    0.23
    gun
    0.22
    ively
    0.20
    tering
    0.20
     fired
    0.20
     Fired
    0.19
    tober
    0.19
    Activations Density 0.023%

    No Known Activations