© 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. 74715
    Prev
    Next
    INDEX
    Explanations

    How-to guides

    np_max-act · gemini-2.0-flash

    This neuron detects general-statement or opinion-introducing phrases (e.g. “They say,” “It’s…,” “There’s…,” “Believe us,” etc.)

    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
     reopened
    -0.07
     Meredith
    -0.07
     Experience
    -0.06
     beef
    -0.06
    Regex
    -0.06
     Người
    -0.06
    (Be
    -0.06
     moet
    -0.06
    experience
    -0.06
    related
    -0.06
    POSITIVE LOGITS
    ns
    0.07
     akin
    0.07
     BTN
    0.06
    .online
    0.06
     FAT
    0.06
     Trab
    0.06
    ोक
    0.06
     sai
    0.06
     لك
    0.06
    fb
    0.06
    Activations Density 0.087%

    No Known Activations