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. 81255
    Prev
    Next
    INDEX
    Explanations

    expected

    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
     Serializer
    -0.07
    市場
    -0.07
    Lady
    -0.06
    Poly
    -0.06
     type
    -0.06
     Tiny
    -0.06
    rz
    -0.06
     відсут
    -0.06
    (cache
    -0.06
    Insensitive
    -0.06
    POSITIVE LOGITS
     \/
    0.07
     nostalgic
    0.07
    ْ
    0.06
    。。
    0.06
     hometown
    0.06
    .apache
    0.06
    故事
    0.06
    ouver
    0.06
    最終
    0.06
    _globals
    0.06
    Activations Density 0.010%

    No Known Activations