© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 13771
    Prev
    Next
    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    This neuron flags tokens that form the abbreviated court‐citation “5TH CIR.” (i.e. the ordinal “TH” plus the “CIR.” marker in appellate citations).

    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
    _Message
    -0.07
    ival
    -0.06
     algebra
    -0.06
    ensible
    -0.06
     stresses
    -0.06
     st
    -0.06
    Finally
    -0.06
     Christian
    -0.06
     dataset
    -0.06
    Logs
    -0.06
    POSITIVE LOGITS
    ‌ای
    0.07
    .ReadInt
    0.06
    _stub
    0.06
     caucus
    0.06
    (tab
    0.06
     subsid
    0.06
     lobby
    0.06
     intl
    0.06
     νεφοκάλυψης
    0.06
     currentItem
    0.06
    Activations Density 0.002%

    No Known Activations