© 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. 29467
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect ordinary conversational text—natural language words in user or assistant turns—as opposed to formatting or control tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    the interactions and recommendations in customer service dialogues related to product purchases.

    oai_token-act-pair · gpt-4o-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
    unread
    -0.07
    ордин
    -0.06
     Riding
    -0.06
    觉
    -0.06
     phê
    -0.06
    git
    -0.06
     shows
    -0.06
    岗
    -0.06
     outdoors
    -0.06
    .getDate
    -0.06
    POSITIVE LOGITS
     심
    0.07
     ।↵↵
    0.07
     milieu
    0.06
    (other
    0.06
    \")
    0.06
     INTO
    0.06
     Dunn
    0.06
     ก
    0.06
     weekend
    0.06
    Accessor
    0.06
    Activations Density 0.045%

    No Known Activations