© 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 EvalsExportsAPI 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. 38341
    Prev
    Next
    INDEX
    Explanations

    root and power problems

    np_max-act · gemini-2.0-flash

    mathematical operations related to roots and powers of numbers.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron activates on tokens representing in‐line decimal numbers (floating-point approximations) in the math text.

    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
     vc
    -0.07
    Depth
    -0.06
    constraints
    -0.06
    jem
    -0.06
    ้ำ
    -0.06
    chyb
    -0.06
     {};
    -0.05
     sla
    -0.05
    ドル
    -0.05
    ibration
    -0.05
    POSITIVE LOGITS
     Alberto
    0.07
    	state
    0.07
    杜
    0.07
    ้นท
    0.07
     ΠΑΝ
    0.07
    思考
    0.07
     deltaTime
    0.07
     slož
    0.06
     �
    0.06
    (relative
    0.06
    Activations Density 0.005%

    No Known Activations