© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 59331
    Prev
    Next
    INDEX
    Explanations

    need want

    np_max-act · gemini-2.0-flash

    This neuron fires on the natural‐language explanatory prose of answer posts (the running English sentences), rather than on code, headings, or question text.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    ProcessEvent
    -0.07
    atypes
    -0.06
    usra
    -0.06
     Daw
    -0.06
     rollout
    -0.06
    eno
    -0.06
    ả
    -0.06
    �
    -0.06
     extraordinary
    -0.06
    badge
    -0.06
    POSITIVE LOGITS
     包
    0.07
    ($
    0.06
     {$
    0.06
    äge
    0.06
     grams
    0.06
    amız
    0.06
    _curr
    0.06
    (FLAGS
    0.06
    姆
    0.06
    照片
    0.06
    Activations Density 0.018%

    No Known Activations