© 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 EvalsExportsinterp-engineNEWAPI 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. 58326
    Prev
    Next
    INDEX
    Explanations

    stellar

    np_max-act · gemini-2.0-flash

    This neuron detects numeric tokens representing floating-point values (i.e., decimal numbers).

    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
     prey
    -0.07
    Č
    -0.06
     řadu
    -0.06
    .but
    -0.06
    _Value
    -0.06
    ็นต
    -0.06
     Raphael
    -0.06
     taşım
    -0.06
     Flooring
    -0.06
     собі
    -0.06
    POSITIVE LOGITS
     fixes
    0.06
    чет
    0.06
     LOCAL
    0.06
    政府
    0.06
    actical
    0.06
    ейств
    0.06
    stellar
    0.06
     ghetto
    0.06
     Grad
    0.06
    Danny
    0.06
    Activations Density 0.001%

    No Known Activations