© 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. 11-RESID-POST-AA
    6. 130058
    Prev
    Next
    INDEX
    Explanations

    time references

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on tokens that signal personal recognition or being remembered (e.g. “recognized me as the person he had talked to before”).

    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
     helmets
    -0.07
     dish
    -0.07
     gö
    -0.07
     outr
    -0.07
    .�
    -0.07
    LEncoder
    -0.07
     tasting
    -0.07
    وع
    -0.06
     pumpkin
    -0.06
    INGTON
    -0.06
    POSITIVE LOGITS
    ็อก
    0.06
     Tune
    0.06
    ‌شوند
    0.06
     [=[
    0.06
    ehr
    0.06
    تماع
    0.06
     exploiting
    0.06
    �
    0.05
    っている
    0.05
    _GPU
    0.05
    Activations Density 0.192%

    No Known Activations