© 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. 59431
    Prev
    Next
    INDEX
    Explanations

    arrested

    np_max-act · gemini-2.0-flash

    This neuron fires on thematic or section‐style nouns (often followed by “of”), such as “study,” “economy,” “unity,” “mining,” or “arrested.”

    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
    	ST
    -0.08
    userManager
    -0.07
     ممن
    -0.07
     noteworthy
    -0.07
     Zuckerberg
    -0.07
     ULONG
    -0.06
     svat
    -0.06
    	category
    -0.06
    Import
    -0.06
    (attr
    -0.06
    POSITIVE LOGITS
     fm
    0.07
     uzav
    0.06
    ifference
    0.06
     polarity
    0.06
    niž
    0.06
    /plugin
    0.06
     inaccurate
    0.06
    -divider
    0.06
     bc
    0.06
    aisal
    0.06
    Activations Density 0.474%

    No Known Activations