© 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. 11-RESID-POST-AA
    6. 105780
    Prev
    Next
    INDEX
    Explanations

    Legal disclaimers

    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
     Knife
    -0.06
     psychiatrist
    -0.06
     Barrel
    -0.06
    _ticket
    -0.06
    аніз
    -0.06
     barrel
    -0.06
     груз
    -0.05
    .abspath
    -0.05
     componentWillUnmount
    -0.05
    ;p
    -0.05
    POSITIVE LOGITS
    Sep
    0.07
     کردم
    0.07
    ชอบ
    0.06
    報
    0.06
    Eb
    0.06
     center
    0.06
     없었다
    0.06
    िसक
    0.06
    olist
    0.06
    (Locale
    0.06
    Activations Density 0.004%

    No Known Activations