© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43309
    Prev
    Next
    INDEX
    Explanations

    [

    np_max-act · gemini-2.0-flash

    The neuron activates on regex metacharacters—brackets, parentheses, braces, angle brackets, etc.—used in pattern expressions.

    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
     dood
    -0.07
    OL
    -0.07
     ux
    -0.06
    PTION
    -0.06
     dying
    -0.06
     direkt
    -0.06
     đức
    -0.06
     Nelson
    -0.06
     uncle
    -0.06
    �부
    -0.06
    POSITIVE LOGITS
    atural
    0.07
    ρωση
    0.07
    เพราะ
    0.07
     mastur
    0.07
    .Zoom
    0.06
     astronomical
    0.06
    Stick
    0.06
    Preview
    0.06
     plán
    0.06
    .progress
    0.06
    Activations Density 0.016%

    No Known Activations