© 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. 13886
    Prev
    Next
    INDEX
    Explanations

    will

    np_max-act · gemini-2.0-flash

    This neuron lights up on marketing-style quantifier phrases—especially promotional copy that spells out options (e.g. “a … for every …”).

    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
    (cls
    -0.07
     furious
    -0.07
     adolescents
    -0.07
     younger
    -0.07
     hàm
    -0.06
     usuario
    -0.06
     young
    -0.06
    akes
    -0.06
    (no
    -0.06
     unnecessary
    -0.06
    POSITIVE LOGITS
     až
    0.06
     кг
    0.06
    θμ
    0.06
    /res
    0.06
     boa
    0.06
    ेग
    0.06
    ()>
    0.06
     Karen
    0.06
    ",-
    0.05
    Youtube
    0.05
    Activations Density 0.072%

    No Known Activations