© 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. 128272
    Prev
    Next
    INDEX
    Explanations

    came

    np_max-act · gemini-2.0-flash

    The neuron is specialized to detect occurrences of the verb “come” (and its inflected forms like “came,” “comes,” “coming,” 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
    >alert
    -0.07
    .getS
    -0.06
     underwear
    -0.06
    /config
    -0.06
    174
    -0.06
    inous
    -0.06
    FD
    -0.06
    /pay
    -0.06
    _errors
    -0.06
    /dr
    -0.06
    POSITIVE LOGITS
     داخ
    0.07
     cig
    0.07
    licenses
    0.07
    manın
    0.06
     �
    0.06
     eksik
    0.06
    очки
    0.06
    ublish
    0.06
     kappa
    0.06
    .pageY
    0.06
    Activations Density 0.094%

    No Known Activations