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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 23423
    Prev
    Next
    INDEX
    Explanations

    phrases related to sexual positions and their implications

    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
     sexuality
    -0.16
     Germ
    -0.14
    OwnProperty
    -0.14
    estre
    -0.14
    ÑĥлÑİ
    -0.14
    θεÏģ
    -0.14
    akk
    -0.13
    rlen
    -0.13
     Saud
    -0.13
     Pert
    -0.13
    POSITIVE LOGITS
     penetration
    0.32
     penetr
    0.27
     missionary
    0.25
     partners
    0.23
     penet
    0.23
    partners
    0.23
    etration
    0.22
     Partners
    0.21
     partner
    0.20
     Pen
    0.20
    Activations Density 0.036%

    No Known Activations