© 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. 29600
    Prev
    Next
    INDEX
    Explanations

    evaluation and analysis

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens—especially isolated numbers and decimal values (e.g., limits, IDs, and performance‐evaluation scores).

    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
    );">↵
    -0.06
     saf
    -0.06
    응
    -0.06
    .Keyboard
    -0.06
    ammed
    -0.06
    ็
    -0.05
    "){
    ↵
    -0.05
     аг
    -0.05
    .getIn
    -0.05
    Comments
    -0.05
    POSITIVE LOGITS
     bytearray
    0.07
    _aug
    0.07
    _clause
    0.07
    -ce
    0.06
     Μ
    0.06
    Seleccion
    0.06
     jMenuItem
    0.06
    guna
    0.06
     учас
    0.06
    _cliente
    0.06
    Activations Density 0.005%

    No Known Activations