© 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. 58650
    Prev
    Next
    INDEX
    Explanations

    Disjointed conversation snippets

    np_max-act · gemini-2.0-flash

    This neuron detects polite closing offers of help (e.g. “Let me know if there’s anything else I can assist you with”).

    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
     Cab
    -0.08
    Mot
    -0.07
    107
    -0.07
    _curve
    -0.07
    fections
    -0.07
    _expect
    -0.06
     continuity
    -0.06
    tax
    -0.06
     Users
    -0.06
     when
    -0.06
    POSITIVE LOGITS
    雙
    0.06
     yaşan
    0.06
     İli
    0.06
     backlog
    0.06
     وغير
    0.06
    ูรณ
    0.06
     resett
    0.06
     rooftop
    0.06
    ंद
    0.06
     phối
    0.06
    Activations Density 0.065%

    No Known Activations