© 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. 130096
    Prev
    Next
    INDEX
    Explanations

    voluntarily

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on language assessing the voluntariness and knowing nature of a guilty plea (e.g., “knowingly,” “voluntarily,” “intelligently entered/made”).

    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
    -kind
    -0.07
    Reusable
    -0.06
     administering
    -0.06
    -util
    -0.06
     Pasadena
    -0.06
    ww
    -0.06
    indicator
    -0.06
    gent
    -0.06
     moss
    -0.06
    _P
    -0.06
    POSITIVE LOGITS
     đứng
    0.07
    caption
    0.07
    agnost
    0.07
    	atomic
    0.07
    uyền
    0.07
     shareholders
    0.06
     smartphone
    0.06
     capit
    0.06
    .Le
    0.06
    OWER
    0.06
    Activations Density 0.002%

    No Known Activations