© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 89144
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    The neuron detects numeric literals (including integers, decimals, and negative values) in code, such as the coordinate and length values found in SVG path definitions.

    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
     لكن
    -0.07
    尖
    -0.06
     nh
    -0.06
    longitude
    -0.06
    REQUEST
    -0.06
     Z
    -0.06
    こんにちは
    -0.06
     Re
    -0.06
     Mass
    -0.06
     FINAL
    -0.06
    POSITIVE LOGITS
     belonged
    0.06
     varlık
    0.06
    IData
    0.06
    nullable
    0.06
    τερ
    0.06
     国家
    0.06
    .loads
    0.06
    .success
    0.06
     bulunur
    0.06
    PLAY
    0.06
    Activations Density 0.003%

    No Known Activations