© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 92310
    Prev
    Next
    INDEX
    Explanations

    mal

    np_max-act · gemini-2.0-flash

    This neuron lightly responds to tokens that look like titles or proper nouns—i.e. capitalized words and abbreviations (often technical terms or names).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    RESSED
    -0.06
     CAM
    -0.06
     impressions
    -0.06
     základní
    -0.06
     côt
    -0.06
    kovi
    -0.06
     혼
    -0.06
    associate
    -0.06
    ूट
    -0.06
     TD
    -0.06
    POSITIVE LOGITS
     seper
    0.06
     ALLOW
    0.06
    ==>
    0.06
     Invitation
    0.06
     paddingLeft
    0.06
    pesan
    0.06
    _probability
    0.06
     links
    0.06
     forgiveness
    0.06
    .Push
    0.06
    Activations Density 0.000%

    No Known Activations