© 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
    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. 108971
    Prev
    Next
    INDEX
    Explanations

    sports teams

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on names of professional sports teams or clubs.

    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
    Allen
    -0.07
    Race
    -0.07
     _
    -0.06
    ”，
    -0.06
     endorse
    -0.06
    İTESİ
    -0.06
     DEFIN
    -0.06
    üle
    -0.06
     hran
    -0.06
    .PL
    -0.06
    POSITIVE LOGITS
     keyed
    0.07
    horizontal
    0.07
    allas
    0.06
    óm
    0.06
    541
    0.06
    оку
    0.06
     coax
    0.06
     زیبا
    0.06
    ipher
    0.06
    ос
    0.06
    Activations Density 0.032%

    No Known Activations