© 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. 126861
    Prev
    Next
    INDEX
    Explanations

    Blogger blogs

    np_max-act · gemini-2.0-flash

    The neuron detects the “noreply@blogger.com” no-reply email address in blog comment metadata.

    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
    (holder
    -0.07
    �
    -0.07
     condom
    -0.07
     keypad
    -0.07
    เตร
    -0.07
     그런
    -0.07
     začí
    -0.07
     وات
    -0.06
     candles
    -0.06
     меч
    -0.06
    POSITIVE LOGITS
    SPORT
    0.06
    860
    0.06
    kel
    0.06
     assembled
    0.06
    $template
    0.06
    _DRIVER
    0.06
    ائي
    0.06
     implic
    0.06
    iteit
    0.06
     громадян
    0.05
    Activations Density 0.000%

    No Known Activations