Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 29847
    Prev
    Next
    INDEX
    Explanations

    references to significant directors and their 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
     Besch
    -0.17
     escorte
    -0.14
     Tradable
    -0.14
    olumn
    -0.13
    belt
    -0.13
    ormsg
    -0.13
    ÎĻÎijÎļ
    -0.13
     trainable
    -0.12
     Fletcher
    -0.12
     foil
    -0.12
    POSITIVE LOGITS
     director
    0.32
     film
    0.29
     directors
    0.29
     filmm
    0.28
    director
    0.26
    film
    0.25
     Directors
    0.24
     Film
    0.24
     films
    0.23
     filmmaker
    0.23
    Activations Density 0.065%

    No Known Activations