© 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. 91450
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    This neuron detects words and phrases used for disclaiming, denying, or clarifying (e.g., “no,” “denied,” “did nothing,” “clarifies”).

    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
    З
    -0.07
    legs
    -0.07
    break
    -0.07
    wd
    -0.07
    cookie
    -0.06
    Effects
    -0.06
     Hud
    -0.06
    89
    -0.06
    password
    -0.06
    RG
    -0.06
    POSITIVE LOGITS
    _IOC
    0.07
     θέση
    0.07
    �
    0.07
    .initializeApp
    0.07
     ballo
    0.06
     raz
    0.06
     aVar
    0.06
     zač
    0.06
     ){
↵
    0.06
    ?>><?
    0.06
    Activations Density 0.041%

    No Known Activations