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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 57970
    Prev
    Next
    INDEX
    Explanations

    computer code/identifiers

    np_max-act · gemini-2.0-flash

    The neuron is primarily triggered by bracket characters—especially parentheses (“(” and “)”).

    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
     SOUTH
    -0.07
    doesn
    -0.07
    tz
    -0.06
     HK
    -0.06
    -co
    -0.06
    	Vector
    -0.06
    :b
    -0.06
    Throws
    -0.06
     rankings
    -0.06
    	Point
    -0.06
    POSITIVE LOGITS
     fiercely
    0.07
     boldly
    0.06
    جات
    0.06
    nowled
    0.06
     bekl
    0.06
    ullan
    0.06
    редит
    0.06
    ulan
    0.06
     tedious
    0.06
    OUSE
    0.06
    Activations Density 0.006%

    No Known Activations