© 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. 59317
    Prev
    Next
    INDEX
    Explanations

    strict

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of Latin taxonomic qualifiers in the form “sensu …,” especially phrases like “sensu stricto” or “sensu lato.”

    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
    .stringify
    -0.07
     sw
    -0.07
    Reduce
    -0.07
    ivel
    -0.06
     Se
    -0.06
    PY
    -0.06
    _multiply
    -0.06
     survival
    -0.06
    -B
    -0.06
     death
    -0.06
    POSITIVE LOGITS
    .inner
    0.08
    CursorPosition
    0.07
    .fullName
    0.07
    insn
    0.07
     İş
    0.06
     kims
    0.06
    改
    0.06
    _GR
    0.06
    0.06
    (get
    0.06
    Activations Density 0.004%

    No Known Activations