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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 110185
    Prev
    Next
    INDEX
    Explanations

    locations

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of beauty‐pageant titles (e.g. “Miss X” or “Mrs. Y”) and their associated winner names.

    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
    -de
    -0.07
    jon
    -0.07
     روز
    -0.06
    gon
    -0.06
     parcel
    -0.06
    退
    -0.06
     editing
    -0.06
     kenn
    -0.06
    ceiving
    -0.06
    _utilities
    -0.06
    POSITIVE LOGITS
     monstr
    0.07
    ونا
    0.07
    **
    0.07
    ultural
    0.06
    ;?></
    0.06
    !!!!!
    0.06
    	REQUIRE
    0.06
     Complexity
    0.06
     слишком
    0.06
     dévelop
    0.06
    Activations Density 0.004%

    No Known Activations