© 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. 110441
    Prev
    Next
    INDEX
    Explanations

    website legal disclaimers

    np_max-act · gemini-2.0-flash

    The neuron fires on words and phrases about checking, testing, ensuring quality or accuracy (and related disclaimers).

    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
     عبدال
    -0.07
     نار
    -0.06
     культури
    -0.06
    etype
    -0.06
    bic
    -0.06
     blas
    -0.06
    звичай
    -0.06
    fullname
    -0.06
     getaway
    -0.06
    Priv
    -0.06
    POSITIVE LOGITS
     choisir
    0.07
     introducing
    0.07
    .DELETE
    0.07
     div
    0.07
     proposing
    0.06
     nhiệt
    0.06
    _linked
    0.06
     تبد
    0.06
    ationale
    0.06
    _serialize
    0.06
    Activations Density 0.136%

    No Known Activations