© 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. 38639
    Prev
    Next
    INDEX
    Explanations

    teams or colors

    np_max-act · gemini-2.0-flash

    This neuron fires on mentions of team or squad names (e.g. “Red Team,” “Blue Team,” “Phoenix Squad,” “Black Division”).

    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
     stadium
    -0.08
    /r
    -0.08
     pink
    -0.07
    (kind
    -0.07
     iron
    -0.07
     Matthias
    -0.07
    _header
    -0.07
     indifferent
    -0.07
    aised
    -0.07
     mixer
    -0.07
    POSITIVE LOGITS
    twig
    0.07
    ậy
    0.06
    izontally
    0.06
     Interfaces
    0.06
     USAGE
    0.06
    YEAR
    0.06
    oen
    0.06
    OperationContract
    0.06
     elegance
    0.06
     inflatable
    0.05
    Activations Density 0.039%

    No Known Activations