© 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. 11-RESID-POST-AA
    11. 89296
    Prev
    Next
    INDEX
    Explanations

    sex

    np_max-act · gemini-2.0-flash

    The neuron activates on the word “sex” and closely related terms (e.g. sexual, sex‐specific, sex determination/differentiation), marking passages about sexual classification or differentiation.

    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
    保持
    -0.06
     (^)(
    -0.06
     نار
    -0.06
     كبيرة
    -0.06
    _HPP
    -0.06
     yaml
    -0.06
    affen
    -0.06
    _COOKIE
    -0.06
    966
    -0.06
    gor
    -0.06
    POSITIVE LOGITS
    พระราช
    0.07
     penis
    0.07
    ]|
    0.07
    刻
    0.07
     arasında
    0.07
     وع
    0.07
     unix
    0.06
    ']
    0.06
    Resize
    0.06
    Gender
    0.06
    Activations Density 0.006%

    No Known Activations