© 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. 56034
    Prev
    Next
    INDEX
    Explanations

    treatment

    np_max-act · gemini-2.0-flash

    terms related to chemical treatments and their effects on materials.

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

    This neuron responds to technical terms for scientific processing or treatment methods (e.g., ultrasonic, thermochemical, pre-treatment).

    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
     THAT
    -0.06
    .rawQuery
    -0.06
    .clientY
    -0.06
    تم
    -0.06
    FRINGEMENT
    -0.06
     Peggy
    -0.06
     करक
    -0.06
     hardcore
    -0.06
    Sector
    -0.06
    kid
    -0.06
    POSITIVE LOGITS
    _STATIC
    0.08
    chez
    0.07
     реак
    0.07
    ané
    0.07
    _private
    0.07
    _tests
    0.06
     yuan
    0.06
     -/↵
    0.06
     braces
    0.06
    isodes
    0.06
    Activations Density 0.026%

    No Known Activations