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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 33000
    Prev
    Next
    INDEX
    Explanations

    clothing

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     colonies
    -0.08
     Mormons
    -0.07
     marginalized
    -0.07
     beam
    -0.07
    ーズ
    -0.07
     casos
    -0.06
     Roma
    -0.06
    judge
    -0.06
    ayla
    -0.06
    ản
    -0.06
    POSITIVE LOGITS
     outfit
    0.14
     outfits
    0.13
     木
    0.07
     vazgeç
    0.06
    发出
    0.06
    Nat
    0.06
     Nit
    0.06
     OB
    0.06
     وق
    0.06
     Oval
    0.06
    Activations Density 0.003%

    No Known Activations