© 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. 124866
    Prev
    Next
    INDEX
    Explanations

    connecting words

    np_max-act · gemini-2.0-flash

    This neuron fires on authors stating they’re newcomers—detecting “I’m new to…”-style introductions in questions.

    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
    .OR
    -0.07
    .localization
    -0.07
    Storage
    -0.07
    adioButton
    -0.06
    untlet
    -0.06
     함수
    -0.06
     onions
    -0.06
     报
    -0.06
    .an
    -0.06
    ця
    -0.06
    POSITIVE LOGITS
     revamped
    0.07
    .calls
    0.06
    razy
    0.06
     принадлеж
    0.06
    端
    0.06
    担当
    0.06
    lla
    0.06
     CallingConvention
    0.06
    queued
    0.06
    اش
    0.06
    Activations Density 0.011%

    No Known Activations