© 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. 40989
    Prev
    Next
    INDEX
    Explanations

    odds

    np_max-act · gemini-2.0-flash

    The neuron fires on terms describing casino odds and the house edge—that is, words about probabilities, payouts, and the casino’s advantage.

    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
     swallowing
    -0.07
     Rav
    -0.06
     такие
    -0.06
    ISTORY
    -0.06
     Parr
    -0.06
    Available
    -0.06
    360
    -0.06
    Longitude
    -0.06
    _fac
    -0.06
     hone
    -0.06
    POSITIVE LOGITS
     overd
    0.08
     odds
    0.07
     yana
    0.06
    ��
    0.06
    Gold
    0.06
     trhu
    0.06
    )).↵
    0.06
     spicy
    0.06
     peníze
    0.06
    险
    0.06
    Activations Density 0.004%

    No Known Activations