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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 88683
    Prev
    Next
    INDEX
    Explanations

    investigator

    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
    363
    -0.07
    /mol
    -0.06
    ăng
    -0.06
     Dum
    -0.06
     Kemp
    -0.06
    rb
    -0.06
     dinners
    -0.06
     dương
    -0.06
     births
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     investigators
    0.07
     lửa
    0.07
     Investig
    0.07
     investigator
    0.07
     inject
    0.07
    caught
    0.06
    -inst
    0.06
    (
    0.06
    ')
    ↵
    0.06
     gusto
    0.06
    Activations Density 0.002%

    No Known Activations