© 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. 126995
    Prev
    Next
    INDEX
    Explanations

    Forum instructions

    np_max-act · gemini-2.0-flash

    This neuron detects interface/navigation cues, especially words like “register” and “link” that prompt clicking or signing up.

    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
     Cur
    -0.07
    saved
    -0.07
    268
    -0.07
     Par
    -0.06
    盗
    -0.06
    _positive
    -0.06
     Braves
    -0.06
    924
    -0.06
    .master
    -0.06
     sick
    -0.06
    POSITIVE LOGITS
    uien
    0.07
     »↵↵
    0.07
     vệ
    0.07
     última
    0.06
     keen
    0.06
    ším
    0.06
     Ln
    0.06
     pounding
    0.06
    \Config
    0.06
     mú
    0.06
    Activations Density 0.000%

    No Known Activations