© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 129735
    Prev
    Next
    INDEX
    Explanations

    Put

    np_max-act · gemini-2.0-flash

    equations or mathematical expressions involving numbers and variables.

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

    This neuron detects commands that arrange or order elements—words like “Sort” or “Put … in … order.”

    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
     range
    -0.07
    /AIDS
    -0.06
    .cols
    -0.06
    	UI
    -0.06
    ASIC
    -0.06
    ерг
    -0.06
    ascar
    -0.06
     статус
    -0.06
    ULAR
    -0.06
    Js
    -0.06
    POSITIVE LOGITS
     pronto
    0.07
     rencontre
    0.07
    께서
    0.07
     Savaşı
    0.07
     possessing
    0.06
     polls
    0.06
     vysvět
    0.06
     عب
    0.06
     spies
    0.06
    _PUT
    0.06
    Activations Density 0.001%

    No Known Activations