© 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. 130144
    Prev
    Next
    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash

    The neuron fires on promotional “for … clients/customers in the … industry” phrasing, i.e. vague marketing claims about serving many customers.

    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
    rav
    -0.07
     cakes
    -0.07
    illow
    -0.06
    价值
    -0.06
    ونی
    -0.06
    кого
    -0.06
     فرو
    -0.06
    DE
    -0.06
     voluntary
    -0.06
    isk
    -0.06
    POSITIVE LOGITS
    (fake
    0.07
    (stream
    0.07
     глаз
    0.07
     янва
    0.07
     unlocks
    0.06
     MLM
    0.06
     Abort
    0.06
    (Syntax
    0.06
    完成
    0.06
     없다
    0.06
    Activations Density 0.016%

    No Known Activations