© 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. 6189
    Prev
    Next
    INDEX
    Explanations

    Market reports and systems

    np_max-act · gemini-2.0-flash

    This neuron detects technical industry or product‐category terms—especially capitalized device, system, and market segment names (e.g. “Monitoring System,” “Battery Monitoring System,” “Devices,” “Market”).

    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
     marginLeft
    -0.08
    fullscreen
    -0.07
     squeezing
    -0.07
     Indexed
    -0.06
    Except
    -0.06
    ičky
    -0.06
    unnable
    -0.06
     compress
    -0.06
    從
    -0.06
     Beg
    -0.06
    POSITIVE LOGITS
     kısa
    0.07
     iii
    0.06
    iểu
    0.06
     Sala
    0.06
    ấc
    0.06
    _angle
    0.06
    个人
    0.06
     pard
    0.06
    :update
    0.06
    _OUT
    0.06
    Activations Density 0.019%

    No Known Activations