© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 59314
    Prev
    Next
    INDEX
    Explanations

    case

    np_max-act · gemini-2.0-flash

    This neuron flags discourse‐marker phrases of the form “in this [X]” (e.g. “in this case,” “in this week”).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    стика
    -0.07
    RowCount
    -0.07
     craftsm
    -0.07
     Destiny
    -0.07
    _substr
    -0.07
     Dropout
    -0.07
     Joyce
    -0.06
     meat
    -0.06
     Providence
    -0.06
     dp
    -0.06
    POSITIVE LOGITS
     совершенно
    0.07
    taient
    0.07
     contacted
    0.07
    玻璃
    0.07
     bogus
    0.07
    .KeyChar
    0.06
    inel
    0.06
    ительным
    0.06
    elementType
    0.06
    alphabet
    0.06
    Activations Density 0.040%

    No Known Activations