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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 58703
    Prev
    Next
    INDEX
    Explanations

    OECD

    np_max-act · gemini-2.0-flash

    The neuron activates on capitalized multi‐letter acronyms for international bodies or groupings (e.g. OECD, G7).

    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
     بای
    -0.07
     پزشکی
    -0.06
     họp
    -0.06
     б
    -0.06
    _UNIT
    -0.06
    ulse
    -0.06
     zwarte
    -0.06
    -п
    -0.06
     bonds
    -0.06
    (bl
    -0.06
    POSITIVE LOGITS
     OECD
    0.08
     llvm
    0.08
    parent
    0.07
     nfl
    0.07
     "|"
    0.07
    .Office
    0.07
    _unlock
    0.07
     Нас
    0.06
     prer
    0.06
     Nord
    0.06
    Activations Density 0.002%

    No Known Activations