© 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. 73944
    Prev
    Next
    INDEX
    Explanations

    autom

    np_max-act · gemini-2.0-flash

    This neuron is triggered by mentions of algebraic or automorphism groups (e.g. “GL(…)”, “Aut(…)”, differential‐operator algebras, etc.).

    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
     proced
    -0.06
    ract
    -0.06
    SQLite
    -0.06
     pratique
    -0.06
    .Release
    -0.06
     Spawn
    -0.06
    uxtap
    -0.06
     wxDefault
    -0.06
     FileName
    -0.06
     ragaz
    -0.06
    POSITIVE LOGITS
    (span
    0.06
     �
    0.06
     огром
    0.06
     flips
    0.06
     DNA
    0.06
    INTEGER
    0.06
    -picture
    0.06
     داشتن
    0.06
     AVL
    0.06
    kes
    0.06
    Activations Density 0.002%

    No Known Activations