© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 124993
    Prev
    Next
    INDEX
    Explanations

    imperfections

    np_max-act · gemini-2.0-flash

    The neuron activates on terms describing makeup application mistakes or flawed cosmetic results (e.g., “caked,” “streaks,” “muddy,” “clogs”).

    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
     �
    -0.07
    )set
    -0.06
     bathing
    -0.06
     กำ
    -0.06
     contexts
    -0.06
     itemprop
    -0.06
    uyễn
    -0.06
     Func
    -0.06
    iloc
    -0.06
     zus
    -0.06
    POSITIVE LOGITS
     disagree
    0.07
     Nah
    0.07
    ==='
    0.06
     =↵
    0.06
     Scout
    0.06
     =="
    0.06
    мир
    0.06
    Joined
    0.06
    OD
    0.06
    ήμερα
    0.06
    Activations Density 0.052%

    No Known Activations