© 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. 59439
    Prev
    Next
    INDEX
    Explanations

    moral

    np_max-act · gemini-2.0-flash

    The neuron activates on normative or policy-related moral language (e.g. words like “ethical,” “moral,” “principles,” “unbiased”).

    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
     gaming
    -0.07
     düzey
    -0.06
    fighter
    -0.06
     Soccer
    -0.06
     Sheikh
    -0.06
     rotating
    -0.05
    scss
    -0.05
     stakes
    -0.05
     ARISING
    -0.05
    кти
    -0.05
    POSITIVE LOGITS
     shaved
    0.07
     любов
    0.07
     creeping
    0.06
     bunun
    0.06
    ОН
    0.06
    CTYPE
    0.06
    νώ
    0.06
    BlockSize
    0.06
    ινε
    0.06
     Gr
    0.06
    Activations Density 0.011%

    No Known Activations