© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 59075
    Prev
    Next
    INDEX
    Explanations

    code or programming

    np_max-act · gemini-2.0-flash

    This neuron detects the small decimal confidence scores (e.g. “2.31640625”) that follow the consistency‐checking questions.

    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
    itudes
    -0.07
    .BorderFactory
    -0.07
    orris
    -0.06
     있는데
    -0.06
     immediate
    -0.06
    anitize
    -0.06
     sous
    -0.06
    -flight
    -0.06
    atra
    -0.06
    Choosing
    -0.06
    POSITIVE LOGITS
    �
    0.06
    .animation
    0.06
     enforced
    0.06
    _tr
    0.06
     EventHandler
    0.06
     stockholm
    0.06
    บาล
    0.06
    раб
    0.06
    關
    0.06
    음
    0.06
    Activations Density 0.003%

    No Known Activations