© 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. 7605
    Prev
    Next
    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash

    This neuron activates on the “*” tokens in C pointer declarations (e.g. the asterisks in function‐pointer and data‐pointer types).

    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
     стил
    -0.08
    攻击
    -0.06
     не
    -0.06
     счит
    -0.06
    Meg
    -0.06
    asının
    -0.06
     その他
    -0.06
     ICU
    -0.06
    _apply
    -0.06
     most
    -0.06
    POSITIVE LOGITS
     Oxygen
    0.06
     QS
    0.06
    _bundle
    0.06
    etSocketAddress
    0.06
     Content
    0.06
     Vienna
    0.06
    /',↵
    0.06
    Dream
    0.06
    ولا
    0.06
     서울특별시
    0.06
    Activations Density 0.004%

    No Known Activations