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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 7-RESID-POST-AA
    11. 43525
    Prev
    Next
    INDEX
    Explanations

    ā

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ive
    -0.07
    ()));↵↵
    -0.07
    (IM
    -0.07
    ......
    -0.06
    _exception
    -0.06
     Stake
    -0.06
     think
    -0.06
    ۱۹۷
    -0.06
     Mey
    -0.06
    Autom
    -0.06
    POSITIVE LOGITS
    ī
    0.10
    ē
    0.08
    ā
    0.08
    ān
    0.07
    _UC
    0.07
    responsive
    0.06
    ū
    0.06
    SMS
    0.06
     quả
    0.06
    .InnerText
    0.06
    Activations Density 0.018%

    No Known Activations