© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 89058
    Prev
    Next
    INDEX
    Explanations

    population demographics

    np_max-act · gemini-2.0-flash

    This neuron is triggered by numeric tokens (especially decimal numbers and percentages) in the census‐style demographic and geographic statistics.

    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
    PRINTF
    -0.06
    τέρα
    -0.06
    ровер
    -0.06
    ěř
    -0.06
    ترل
    -0.06
    :";
    ↵
    -0.06
    ="#"
    -0.06
    QUEUE
    -0.06
     ":"
    -0.06
     voiture
    -0.06
    POSITIVE LOGITS
    �
    0.07
     önemli
    0.06
     Báo
    0.06
    pert
    0.06
    cat
    0.06
     nah
    0.06
     fundament
    0.06
     Pred
    0.06
     nurt
    0.06
     Tenn
    0.06
    Activations Density 0.001%

    No Known Activations