© 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. 11-RESID-POST-AA
    11. 57849
    Prev
    Next
    INDEX
    Explanations

    positive descriptions

    np_max-act · gemini-2.0-flash

    references to age and descriptions of youthful characteristics.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects mentions of a young age (numeric age tokens) combined with descriptors implying a minor (e.g. “6 year old beautiful…”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    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
    ится
    -0.07
    ，为
    -0.07
    _fa
    -0.07
    bred
    -0.07
     ده
    -0.07
     antibiotic
    -0.06
     hearts
    -0.06
     são
    -0.06
    ')}}">↵
    -0.06
     Actress
    -0.06
    POSITIVE LOGITS
     Ahmad
    0.07
     explan
    0.06
    ↵
    0.06
    _deploy
    0.06
     Finn
    0.06
    ?“
    0.06
    Energy
    0.06
    滑
    0.06
     scout
    0.06
    开发
    0.06
    Activations Density 0.046%

    No Known Activations