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. 81214
    Prev
    Next
    INDEX
    Explanations

    to

    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
     長
    -0.07
     manager
    -0.06
     sincere
    -0.06
    Two
    -0.06
    893
    -0.06
     Chr
    -0.06
    Polygon
    -0.06
     cực
    -0.06
     Advocate
    -0.06
     articulated
    -0.06
    POSITIVE LOGITS
    userService
    0.07
     impair
    0.07
     monet
    0.07
    )a
    0.07
     thắng
    0.07
    nts
    0.07
    (blob
    0.07
    ynamo
    0.06
     entra
    0.06
    /client
    0.06
    Activations Density 0.018%

    No Known Activations