© 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. 89595
    Prev
    Next
    INDEX
    Explanations

    social issues and race

    np_max-act · gemini-2.0-flash

    This neuron responds to structural/instruction tokens—especially numbers, parentheses, and special header markers—used in the prompt formatting.

    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
     hurricane
    -0.06
     založ
    -0.06
     paramount
    -0.06
     자료
    -0.06
    .ImageAlign
    -0.06
     observable
    -0.06
    ichel
    -0.06
     Litecoin
    -0.06
     люд
    -0.06
     malls
    -0.06
    POSITIVE LOGITS
     depois
    0.07
     dermat
    0.07
    -Series
    0.07
     Amerika
    0.07
    珍
    0.07
     Iterator
    0.06
     Session
    0.06
     hdc
    0.06
     transitioning
    0.06
    _expression
    0.06
    Activations Density 0.007%

    No Known Activations