© 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. 93787
    Prev
    Next
    INDEX
    Explanations

    to

    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
     els
    -0.07
     referenced
    -0.07
    -wsj
    -0.07
    _nums
    -0.07
    ';
    -0.06
     isten
    -0.06
    zen
    -0.06
    ่อ
    -0.06
    άζ
    -0.06
     Og
    -0.06
    POSITIVE LOGITS
     SESSION
    0.07
    _attach
    0.07
    口
    0.06
    StateChanged
    0.06
     usefulness
    0.06
     Stability
    0.06
    -social
    0.06
    言
    0.06
     Dice
    0.06
     financially
    0.06
    Activations Density 0.019%

    No Known Activations