© 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. 55873
    Prev
    Next
    INDEX
    Explanations

    pass

    np_max-act · gemini-2.0-flash

    The neuron detects imperative driving commands (e.g. “PRESS GAS,” “BRAKE,” “TURN LEFT/RIGHT,” “CHANGE LANES,” “OVERTAKE”).

    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
     Ivy
    -0.07
     artist
    -0.07
     artists
    -0.06
     jokes
    -0.06
    urse
    -0.06
     clim
    -0.06
     comedic
    -0.06
     Golden
    -0.06
    λόγ
    -0.06
     song
    -0.06
    POSITIVE LOGITS
     недостат
    0.08
     دستگاه
    0.07
    */↵
    0.07
    .dataset
    0.07
     позд
    0.07
     الاقتص
    0.06
    IDER
    0.06
    хови
    0.06
    .fast
    0.06
    اءة
    0.06
    Activations Density 0.003%

    No Known Activations