© 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. 108916
    Prev
    Next
    INDEX
    Explanations

    calculations

    np_max-act · gemini-2.0-flash

    calculations related to chemical reactions and stoichiometry.

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

    This neuron detects special metadata/control tokens (e.g. header and end-of-text markers) used to structure the conversation.

    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
     hung
    -0.07
     electrode
    -0.07
    ेद
    -0.07
    ptrdiff
    -0.07
     evenings
    -0.06
     hugs
    -0.06
    emed
    -0.06
    ande
    -0.06
    荷
    -0.06
     Android
    -0.06
    POSITIVE LOGITS
     pageCount
    0.07
    eparator
    0.06
    area
    0.06
    	assertNotNull
    0.06
     biraz
    0.06
    .FloatField
    0.06
     QIcon
    0.06
    ("("
    0.06
    ('|
    0.06
     DirectoryInfo
    0.06
    Activations Density 0.027%

    No Known Activations