© 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. 7-RESID-POST-AA
    11. 64888
    Prev
    Next
    INDEX
    Explanations

    online forum discussions

    np_max-act · gemini-2.0-flash

    the neuron detects past-tense verb forms (tokens corresponding to "-ed" endings and nearby tokens indicating completed actions).

    oai_token-act-pair · gpt-5-mini
    Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Finder
    -0.07
    application
    -0.06
    ursors
    -0.06
    inters
    -0.06
    ิตร
    -0.06
    CharCode
    -0.06
     decide
    -0.06
     hadn
    -0.06
     smelled
    -0.06
    Training
    -0.06
    POSITIVE LOGITS
    ":@"
    0.06
     lobbying
    0.06
    `()
    0.06
     liken
    0.06
     NSF
    0.06
    лися
    0.06
     british
    0.05
     उसन
    0.05
     GameManager
    0.05
    rello
    0.05
    Activations Density 0.213%

    No Known Activations