© 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. 89572
    Prev
    Next
    INDEX
    Explanations

    Challenger

    np_max-act · gemini-2.0-flash

    The neuron activates on references to professional tennis circuits and tournament tiers (e.g. ATP, Challenger, Futures, ITF, Grand Prix).

    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
     coron
    -0.07
     náz
    -0.07
     ])↵↵
    -0.07
     Suzanne
    -0.07
     localize
    -0.07
     Freeze
    -0.07
     buffer
    -0.07
    _pres
    -0.07
     Scient
    -0.07
     alist
    -0.07
    POSITIVE LOGITS
    ウォ
    0.06
    .ok
    0.06
    撤
    0.06
    weather
    0.06
     Yorkers
    0.06
    (QWidget
    0.06
    nodeValue
    0.06
    \R
    0.06
    (moment
    0.05
    젝트
    0.05
    Activations Density 0.003%

    No Known Activations