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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 57841
    Prev
    Next
    INDEX
    Explanations

    Innovation and creativity

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the root “creativ” (as in “creative,” “creativity,” “Kreativität,” etc.).

    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
     FName
    -0.06
    stories
    -0.06
     modern
    -0.06
     movie
    -0.06
     Fighters
    -0.06
    undan
    -0.06
     мужчин
    -0.06
    가요
    -0.06
     textView
    -0.06
     backs
    -0.06
    POSITIVE LOGITS
     فصل
    0.07
    jab
    0.07
    Files
    0.07
    าภ
    0.06
     Decrypt
    0.06
    ocrine
    0.06
    .parsers
    0.06
    Public
    0.06
    xED
    0.06
    jav
    0.06
    Activations Density 0.053%

    No Known Activations