© 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 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. 7-RESID-POST-AA
    11. 95512
    Prev
    Next
    INDEX
    Explanations

    first person questions

    np_max-act · gemini-2.0-flash

    It detects user-style questions or interrogative phrases, especially those framed in the first person (e.g., "How/Do I...?/What do I...").

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
     cpp
    -0.08
    commended
    -0.07
    }{
    -0.07
     Worm
    -0.07
    prefer
    -0.06
    <Comment
    -0.06
     usable
    -0.06
     degrade
    -0.06
    _FACTOR
    -0.06
     retain
    -0.06
    POSITIVE LOGITS
     viện
    0.07
     ")");↵
    0.06
    -me
    0.06
     Buen
    0.06
    太郎
    0.06
    Forbidden
    0.06
     جم
    0.06
    Rub
    0.06
     değerli
    0.06
     skull
    0.06
    Activations Density 0.122%

    No Known Activations