© 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. 129893
    Prev
    Next
    INDEX
    Explanations

    How

    np_max-act · gemini-2.0-flash

    This neuron activates on the question word “How,” marking the start of “How”-based 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
     Markt
    -0.06
     era
    -0.06
    istické
    -0.06
    sil
    -0.06
     món
    -0.06
    .RightToLeft
    -0.06
     Ig
    -0.06
    SSID
    -0.05
    (Text
    -0.05
    */),
    -0.05
    POSITIVE LOGITS
    лен
    0.07
     assessments
    0.06
    Safe
    0.06
     нап
    0.06
     undertake
    0.06
    ")
    0.06
    카지노
    0.06
    information
    0.06
     appointment
    0.06
     consolidated
    0.06
    Activations Density 0.009%

    No Known Activations