© 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. 72231
    Prev
    Next
    INDEX
    Explanations

    OC

    np_max-act · gemini-2.0-flash

    This neuron detects out-of-character instruction markers (e.g., “OC” or “ooc”).

    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
    합니다
    -0.07
     така
    -0.06
    .googleapis
    -0.06
     Solic
    -0.06
    .cd
    -0.06
    APO
    -0.06
    므로
    -0.06
     contractual
    -0.06
     Share
    -0.06
    [Math
    -0.06
    POSITIVE LOGITS
     overclock
    0.07
    oe
    0.07
    ka
    0.06
    ,test
    0.06
     wet
    0.06
    cret
    0.06
     exhibiting
    0.06
     Seb
    0.06
     economies
    0.06
     tes
    0.06
    Activations Density 0.001%

    No Known Activations