© 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. 89353
    Prev
    Next
    INDEX
    Explanations

    cref

    np_max-act · gemini-2.0-flash

    This neuron detects XML documentation cross‐reference tags by spotting “cref=” attributes inside `<see>` (and similar) doc comments.

    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
     Mineral
    -0.07
     omission
    -0.07
    йн
    -0.06
    actionDate
    -0.06
     τρό
    -0.06
     heroin
    -0.06
    Ny
    -0.06
    mill
    -0.06
     طر
    -0.06
     δια
    -0.06
    POSITIVE LOGITS
     cref
    0.13
     ΔE
    0.06
    .distance
    0.06
     Neon
    0.06
     сильно
    0.06
     Rencontres
    0.06
     cong
    0.06
    冰
    0.06
     Galaxy
    0.06
    (csv
    0.06
    Activations Density 0.000%

    No Known Activations