© 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. 59284
    Prev
    Next
    INDEX
    Explanations

    of the

    np_max-act · gemini-2.0-flash

    The neuron fires on words describing organizational changes—especially mergers, formations, and restructurings of parties or agencies.

    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
    creenshot
    -0.06
    deny
    -0.06
    Late
    -0.06
     gratuito
    -0.06
     Yep
    -0.06
     připoj
    -0.06
     subur
    -0.06
     Delicious
    -0.06
    名稱
    -0.06
    isions
    -0.06
    POSITIVE LOGITS
    .sul
    0.07
     متعدد
    0.06
     parachute
    0.06
     bằng
    0.06
     작은
    0.06
    ?>>↵
    0.06
     làn
    0.06
     польз
    0.06
    Если
    0.06
    CSI
    0.06
    Activations Density 0.024%

    No Known Activations