© 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. 57855
    Prev
    Next
    INDEX
    Explanations

    suggestions

    np_max-act · gemini-2.0-flash

    This neuron detects customer‐service style apology and resolution statements (e.g., “we apologize for… and offer to…”).

    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
     Leaf
    -0.07
    ountain
    -0.07
     lux
    -0.07
    (loc
    -0.06
     meta
    -0.06
     parsed
    -0.06
    Comb
    -0.06
    vre
    -0.06
     Hawai
    -0.06
    hatt
    -0.06
    POSITIVE LOGITS
     buluş
    0.07
    _allocation
    0.06
    чивается
    0.06
     تلك
    0.06
     العامة
    0.06
    ImageUrl
    0.06
    Buying
    0.06
     рассказ
    0.06
     О
    0.06
     겁
    0.05
    Activations Density 0.070%

    No Known Activations