© 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. 42919
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    This neuron selectively activates on the word “OUT,” especially as it appears in legal/license boilerplate phrases like “out of or in ….”

    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
    KeyEvent
    -0.07
     Chair
    -0.06
    _AG
    -0.06
    Ticker
    -0.06
     wild
    -0.06
     Seat
    -0.06
     algae
    -0.06
     BlockPos
    -0.06
     между
    -0.06
    106
    -0.06
    POSITIVE LOGITS
    <f
    0.07
    ampler
    0.07
     offending
    0.06
    _todo
    0.06
    ánu
    0.06
    ]')↵
    0.06
     захворю
    0.06
    рас
    0.06
     مجموعه
    0.06
     preparedStatement
    0.06
    Activations Density 0.001%

    No Known Activations