© 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. 57604
    Prev
    Next
    INDEX
    Explanations

    winners

    np_max-act · gemini-2.0-flash

    The neuron detects the “Winners (and nominees)” headings or labels in award descriptions.

    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
     Jean
    -0.07
    forc
    -0.06
     Scoped
    -0.06
    Ctrls
    -0.06
     phi
    -0.06
     zách
    -0.06
    cimal
    -0.06
     chill
    -0.06
    _bd
    -0.06
     Guarantee
    -0.06
    POSITIVE LOGITS
     winners
    0.10
     winner
    0.09
     Winner
    0.08
    REE
    0.08
    serialize
    0.07
    ree
    0.07
    pově
    0.07
     Innov
    0.07
    capitalize
    0.07
     Amount
    0.06
    Activations Density 0.011%

    No Known Activations