© 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. 15665
    Prev
    Next
    INDEX
    Explanations

    references to film ratings and standards regarding sexual content

    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
    รว
    -0.15
    xCD
    -0.14
    ptal
    -0.14
    èij
    -0.14
    dorf
    -0.13
     steal
    -0.13
     statuses
    -0.13
    oment
    -0.13
     *)((
    -0.13
     Ballard
    -0.13
    POSITIVE LOGITS
     rating
    0.31
     Rating
    0.28
     censor
    0.28
     ratings
    0.28
     rated
    0.27
     content
    0.27
    Rating
    0.27
     age
    0.27
     Ratings
    0.26
     Rated
    0.26
    Activations Density 0.051%

    No Known Activations