© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 41017
    Prev
    Next
    INDEX
    Explanations

    other

    np_max-act · gemini-2.0-flash

    This neuron detects generic list or “miscellaneous” markers—words like “other,” “etc.,” and similar tokens used to indicate additional or unspecified items in a list.

    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
    iei
    -0.07
    cation
    -0.07
    atro
    -0.07
    adget
    -0.07
    124
    -0.06
    avr
    -0.06
    КИ
    -0.06
    라고
    -0.06
    럴
    -0.06
    زر
    -0.06
    POSITIVE LOGITS
    UnitTest
    0.07
     Cove
    0.07
     Instructor
    0.06
    _train
    0.06
     rpm
    0.06
    	mock
    0.06
    _centers
    0.06
    染
    0.06
     recruiting
    0.06
     plage
    0.06
    Activations Density 0.041%

    No Known Activations