© 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. 59254
    Prev
    Next
    INDEX
    Explanations

    Soc

    np_max-act · gemini-2.0-flash

    This neuron identifies occurrences of academic journal citation strings (e.g., “J. Am. Chem. Soc.”).

    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
    ´t
    -0.08
    /pr
    -0.07
     einen
    -0.07
    िष
    -0.06
    итися
    -0.06
     samp
    -0.06
     glGen
    -0.06
    Bài
    -0.06
     pelos
    -0.06
    าพ
    -0.06
    POSITIVE LOGITS
     Compact
    0.07
    Closing
    0.07
    //------------------------------------------------------------------------------------------------
    0.07
     Col
    0.07
     Unexpected
    0.07
    unwrap
    0.06
     garments
    0.06
     regulation
    0.06
    _wrapper
    0.06
    istics
    0.06
    Activations Density 0.002%

    No Known Activations