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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 13930
    Prev
    Next
    INDEX
    Explanations

    news.ycombinator.com

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect URL components (e.g. “://”, domain parts like “com” or “news.ycombinator.com”, path tokens, etc.) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _SHOW
    -0.07
    Evt
    -0.07
    Lint
    -0.07
     Thank
    -0.07
     Woo
    -0.06
     stage
    -0.06
     duk
    -0.06
     Pret
    -0.06
    	D
    -0.06
    рім
    -0.06
    POSITIVE LOGITS
    placer
    0.07
    .commands
    0.06
    digit
    0.06
     Azure
    0.06
     hu
    0.06
     підтрим
    0.06
     IDisposable
    0.06
     medicine
    0.06
    .goal
    0.06
     upgrades
    0.06
    Activations Density 0.015%

    No Known Activations