© 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. 89148
    Prev
    Next
    INDEX
    Explanations

    Decimal numbers

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on any numeric‐related token (digits, fractions, negative signs, etc.), effectively detecting numbers or numeric 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
    Already
    -0.07
     period
    -0.07
    �
    -0.07
     менее
    -0.06
    noise
    -0.06
     staying
    -0.06
    ök
    -0.06
     отмет
    -0.06
     libros
    -0.06
     Sand
    -0.06
    POSITIVE LOGITS
     Directions
    0.07
    جد
    0.07
    ～↵↵
    0.07
     hastalık
    0.07
    ....↵↵
    0.07
    ター
    0.07
    敢
    0.07
    ในส
    0.07
    ์ฟ
    0.06
    chy
    0.06
    Activations Density 0.011%

    No Known Activations