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. 104370
    Prev
    Next
    INDEX
    Explanations

    HTML/XML tags

    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
    Sprites
    -0.07
     Hardcover
    -0.07
    恨
    -0.06
    andest
    -0.06
    _FT
    -0.06
    variables
    -0.06
    _barrier
    -0.06
     baja
    -0.06
     Probably
    -0.06
    	stmt
    -0.06
    POSITIVE LOGITS
     svého
    0.07
    ա
    0.07
    illes
    0.06
    ooky
    0.06
     boils
    0.06
    userName
    0.06
     skon
    0.06
    914
    0.06
     il
    0.06
     νέ
    0.06
    Activations Density 0.020%

    No Known Activations