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. 104307
    Prev
    Next
    INDEX
    Explanations

    H

    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
     Fab
    -0.07
    rell
    -0.07
    ceptions
    -0.07
    _inner
    -0.07
    ่าอ
    -0.06
     Vern
    -0.06
    fixtures
    -0.06
    STR
    -0.06
    Roman
    -0.06
     Operator
    -0.06
    POSITIVE LOGITS
     часа
    0.07
    $fields
    0.06
     kullanıcı
    0.06
     psik
    0.06
     شه
    0.06
     дома
    0.06
     çarp
    0.06
    ))/(
    0.06
    oliday
    0.06
     manually
    0.06
    Activations Density 0.091%

    No Known Activations