© 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. 110693
    Prev
    Next
    INDEX
    Explanations

    technology and business

    np_max-act · gemini-2.0-flash

    This neuron responds to high-frequency function words (e.g., articles and conjunctions).

    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
     indicators
    -0.07
     ros
    -0.07
    HP
    -0.07
     teased
    -0.07
     Ham
    -0.07
    DDS
    -0.07
    ha
    -0.07
     laz
    -0.07
    Frozen
    -0.07
    φων
    -0.07
    POSITIVE LOGITS
     timeframe
    0.07
     possível
    0.06
    <head
    0.06
     }?>↵
    0.06
     bbox
    0.06
    ’:
    0.06
    EndInit
    0.06
    Responses
    0.06
     гара
    0.06
     Pero
    0.06
    Activations Density 0.183%

    No Known Activations