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. 21855
    Prev
    Next
    INDEX
    Explanations

    Travel packing

    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
    BH
    -0.07
     perish
    -0.07
    arak
    -0.06
    ENGINE
    -0.06
     Titanic
    -0.06
    SU
    -0.06
     funded
    -0.06
    MK
    -0.06
     duct
    -0.06
     نیاز
    -0.06
    POSITIVE LOGITS
     ceiling
    0.07
     سمت
    0.06
     francaise
    0.06
    '<
    0.06
    :=
    0.06
    -Series
    0.06
     tehlik
    0.06
    �
    0.06
     furnished
    0.06
    DECLARE
    0.06
    Activations Density 0.015%

    No Known Activations