Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 79703
    Prev
    Next
    INDEX
    Explanations

    playwright

    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
     Mode
    -0.08
     DateFormatter
    -0.06
     베
    -0.06
     homosex
    -0.06
     WIFI
    -0.06
    面積
    -0.06
    Č
    -0.06
    .Controls
    -0.06
     bufsize
    -0.06
    暖
    -0.06
    POSITIVE LOGITS
    (inputs
    0.07
    хран
    0.07
    ovna
    0.07
    Drink
    0.07
    poss
    0.07
    athering
    0.07
     dram
    0.06
     pumpkin
    0.06
    claim
    0.06
     play
    0.06
    Activations Density 0.003%

    No Known Activations