© 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. 59420
    Prev
    Next
    INDEX
    Explanations

    aviation/events

    np_max-act · gemini-2.0-flash

    This neuron activates on technical terms, especially alphanumeric model numbers and specialized acronyms.

    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
     fatt
    -0.07
     意
    -0.06
     Flynn
    -0.06
    ilm
    -0.06
     Toll
    -0.06
    pager
    -0.06
    _positive
    -0.06
     positivity
    -0.06
     antivirus
    -0.06
     lac
    -0.06
    POSITIVE LOGITS
    NewUrlParser
    0.07
     Extr
    0.06
    .FormStartPosition
    0.06
     aracılığıyla
    0.06
    =pk
    0.06
    community
    0.06
    (Global
    0.06
    (Core
    0.06
     بودن
    0.06
    �
    0.06
    Activations Density 0.711%

    No Known Activations