© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 93794
    Prev
    Next
    INDEX
    Explanations

    period

    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
     joy
    -0.06
    [@
    -0.06
    +)
    -0.06
     �
    -0.06
    <K
    -0.06
    ’y
    -0.06
     *,
    -0.06
     [{'
    -0.06
    �
    -0.06
     الز
    -0.06
    POSITIVE LOGITS
     Directive
    0.06
    438
    0.06
    очного
    0.06
    apo
    0.06
    deposit
    0.06
    UTO
    0.06
    buch
    0.06
     Liverpool
    0.06
    pc
    0.06
     immoral
    0.06
    Activations Density 0.005%

    No Known Activations