© 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. 55426
    Prev
    Next
    INDEX
    Explanations

    18

    np_max-act · gemini-2.0-flash

    This neuron detects numeric age‐range indicators in demographic passages (e.g. the “18” in “under the age of 18”).

    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
     Gregory
    -0.06
    UTURE
    -0.06
    Boundary
    -0.06
     missions
    -0.06
     utilization
    -0.06
     por
    -0.06
     política
    -0.06
     Religion
    -0.06
    Votre
    -0.06
    kea
    -0.06
    POSITIVE LOGITS
     Jail
    0.06
    ระด
    0.06
    ‐‐
    0.06
     ممن
    0.06
     soruml
    0.06
    ([$
    0.06
     psychic
    0.06
    hwnd
    0.06
    /apt
    0.06
    	Close
    0.06
    Activations Density 0.000%

    No Known Activations