© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 58315
    Prev
    Next
    INDEX
    Explanations

    emotions

    np_max-act · gemini-2.0-flash

    This neuron detects emotionally charged words and expressions of feelings (e.g., grief, sadness, emotions) in supportive or empathetic contexts.

    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
     Mang
    -0.06
     фон
    -0.06
    uled
    -0.06
     Marx
    -0.06
    用户
    -0.06
     clip
    -0.06
    Pel
    -0.06
     Reyes
    -0.06
     derivatives
    -0.06
     Buffered
    -0.06
    POSITIVE LOGITS
    -backend
    0.07
    -percent
    0.07
    ophobic
    0.07
    /Private
    0.07
    ∠
    0.07
     segundo
    0.07
    iterator
    0.07
    faction
    0.07
     것으로
    0.06
    ;i
    0.06
    Activations Density 0.112%

    No Known Activations