© 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. 56039
    Prev
    Next
    INDEX
    Explanations

    okay

    np_max-act · gemini-2.0-flash

    dialogue that reflects playful, suggestive, and flirtatious interactions.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on conversational “filler” or acknowledgement tokens—words like “okay,” “right,” “yes,” “just,” or similar short discourse markers indicating agreement or alignment.

    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
     Henderson
    -0.07
     vỏ
    -0.06
    _publish
    -0.06
    카지노
    -0.06
    Unfortunately
    -0.06
    Rick
    -0.06
    bens
    -0.06
     lexer
    -0.06
     dyst
    -0.06
     responseBody
    -0.06
    POSITIVE LOGITS
    	Serial
    0.08
     explosion
    0.07
    ”.↵↵
    0.07
    level
    0.07
     çöz
    0.07
    ：「
    0.06
     figures
    0.06
     Dot
    0.06
    ॰
    0.06
    play
    0.06
    Activations Density 0.024%

    No Known Activations