Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 80839
    Prev
    Next
    INDEX
    Explanations

    interle

    np_max-act · gemini-2.0-flash
    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
     zahl
    -0.06
     Bayern
    -0.06
     사망
    -0.06
     denomin
    -0.06
     πρό
    -0.06
     zona
    -0.06
    계획
    -0.06
    (){
    ↵
    -0.06
    achten
    -0.06
    omen
    -0.06
    POSITIVE LOGITS
    oling
    0.07
     Vlad
    0.07
    няв
    0.07
    레
    0.07
    le
    0.07
    slack
    0.07
    .backward
    0.07
     interle
    0.06
    خي
    0.06
    нями
    0.06
    Activations Density 0.001%

    No Known Activations