© 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. 91338
    Prev
    Next
    INDEX
    Explanations

    rules and consequences

    np_max-act · gemini-2.0-flash

    The neuron fires on formal legal or contractual terms—especially words referring to clauses, lock-in periods, and related provisions.

    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
     nature
    -0.07
     maar
    -0.07
     Configure
    -0.07
     Andersen
    -0.06
    .Executor
    -0.06
    рал
    -0.06
    [text
    -0.06
    Tab
    -0.06
    αρ
    -0.06
    tearDown
    -0.06
    POSITIVE LOGITS
     teste
    0.06
    กล
    0.06
    _fixed
    0.06
    vel
    0.06
     Oval
    0.06
    Primary
    0.06
    ندا
    0.06
    ergarten
    0.06
    UniformLocation
    0.06
    :])↵
    0.06
    Activations Density 0.241%

    No Known Activations