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. 81215
    Prev
    Next
    INDEX
    Explanations

    DataTable

    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
     CONSTRAINT
    -0.07
    idence
    -0.07
    -e
    -0.06
     cause
    -0.06
     صاد
    -0.06
     instance
    -0.06
     kuk
    -0.06
     syndrome
    -0.06
    _de
    -0.06
    çon
    -0.06
    POSITIVE LOGITS
     Garrett
    0.07
     Voy
    0.06
    ulfill
    0.06
    oly
    0.06
     cellspacing
    0.06
     arranged
    0.06
     확실
    0.06
    培训
    0.06
     �
    0.06
     trabajar
    0.06
    Activations Density 0.003%

    No Known Activations