© 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. 43063
    Prev
    Next
    INDEX
    Explanations

    Questions about specifics

    np_max-act · gemini-2.0-flash

    greetings and inquiries about assistance or help.

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

    This neuron fires on words used when asking for clarification or specifying details in a request (e.g., “what,” “specific,” “tasks”).

    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
     becer
    -0.07
    」的
    -0.07
     Legendary
    -0.06
     전에
    -0.06
     leur
    -0.06
    난
    -0.06
    (numero
    -0.06
    _frontend
    -0.06
     Wor
    -0.06
     metro
    -0.06
    POSITIVE LOGITS
     conjunto
    0.07
    elem
    0.06
     NSA
    0.06
    .Remote
    0.06
     directions
    0.06
     spokesman
    0.06
    adium
    0.06
     рівня
    0.06
    偶
    0.06
     rod
    0.06
    Activations Density 0.036%

    No Known Activations