© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 41392
    Prev
    Next
    INDEX
    Explanations

    analytics imports

    np_max-act · gemini-2.0-flash

    elements related to error handling and logging in software development.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron flags references to telemetry, analytics, or monitoring/instrumentation code (e.g. imports or calls related to metrics, auditing, or telemetry).

    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
    Prior
    -0.07
     باق
    -0.07
    stories
    -0.06
    oč
    -0.06
    poz
    -0.06
    -minute
    -0.06
    inae
    -0.06
     Living
    -0.06
     hundreds
    -0.06
    전
    -0.06
    POSITIVE LOGITS
     Москва
    0.07
    _WATER
    0.07
    ---</
    0.07
     ┃
    0.07
    -Re
    0.06
    哦
    0.06
    ائرة
    0.06
     доктор
    0.06
     مرکز
    0.06
    文化
    0.06
    Activations Density 0.045%

    No Known Activations