© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 56267
    Prev
    Next
    INDEX
    Explanations

    of some

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens that express quantity or amount (e.g. “some,” “one,” “more,” “most,” “only,” etc.).

    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
    _rename
    -0.07
    -ph
    -0.06
    olon
    -0.06
    .Buffered
    -0.06
     Megan
    -0.06
    �
    -0.06
    Zero
    -0.06
    ographies
    -0.06
     email
    -0.06
    Lou
    -0.06
    POSITIVE LOGITS
    -approved
    0.06
     rnd
    0.06
     Thema
    0.06
    .ReadInt
    0.06
     وع
    0.06
    _FROM
    0.06
    Reason
    0.06
     Сим
    0.06
     unfair
    0.06
    IEWS
    0.06
    Activations Density 0.257%

    No Known Activations