© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 93866
    Prev
    Next
    INDEX
    Explanations

    Diablo

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lever
    -0.06
    oufl
    -0.06
     entert
    -0.06
     escapes
    -0.06
     ['
    -0.06
     path
    -0.06
     �
    -0.06
    AI
    -0.06
    (lib
    -0.06
    (version
    -0.06
    POSITIVE LOGITS
     Diablo
    0.19
     Hubbard
    0.16
    -Cola
    0.12
     Overwatch
    0.10
    ablo
    0.10
     малень
    0.09
    inct
    0.08
     fastball
    0.08
    ائب
    0.07
    币
    0.07
    Activations Density 0.002%

    No Known Activations