© 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. 59266
    Prev
    Next
    INDEX
    Explanations

    cookie

    np_max-act · gemini-2.0-flash

    This neuron specifically detects mentions of the word “cookie” (or its plural “cookies”) in the 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
    ruitment
    -0.07
     Mathematics
    -0.07
     MAP
    -0.07
     Durham
    -0.07
    NA
    -0.07
     Mann
    -0.07
    789
    -0.07
     Maths
    -0.07
     assessment
    -0.07
     розум
    -0.07
    POSITIVE LOGITS
     cookie
    0.10
    Cookie
    0.08
     dahi
    0.08
    ující
    0.07
    cı
    0.07
     cookies
    0.07
     Cookie
    0.07
    cookie
    0.07
    lie
    0.07
     COOKIE
    0.07
    Activations Density 0.005%

    No Known Activations