© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 56975
    Prev
    Next
    INDEX
    Explanations

    Date and time formats

    np_max-act · gemini-2.0-flash

    This neuron detects tokens representing numbers or numeric values in the text.

    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
     forefront
    -0.06
    -major
    -0.06
    pectrum
    -0.06
     garden
    -0.06
    완료
    -0.06
     Parameter
    -0.06
    -0.06
    Fire
    -0.06
    _No
    -0.06
     soy
    -0.06
    POSITIVE LOGITS
     capitalize
    0.07
    xdc
    0.07
    _CMD
    0.06
     Obesity
    0.06
    erview
    0.06
     MSR
    0.06
    люч
    0.06
     mate
    0.06
     entails
    0.06
     Мі
    0.06
    Activations Density 0.033%

    No Known Activations