© 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 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. 56735
    Prev
    Next
    INDEX
    Explanations

    Chemical compounds and drug discovery

    np_max-act · gemini-2.0-flash

    The neuron specializes in spotting fragments of systematic chemical names—especially multi‐part substituent and backbone tokens in IUPAC‐style compound names.

    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
    ◆
    -0.07
     آل
    -0.07
    coes
    -0.07
     سنت
    -0.07
     fees
    -0.06
     plane
    -0.06
     Claude
    -0.06
     serr
    -0.06
    (res
    -0.06
    rones
    -0.06
    POSITIVE LOGITS
    ━�
    0.06
    ัณฑ
    0.06
    uspended
    0.06
     specializes
    0.06
    凝
    0.06
    воля
    0.06
     Chill
    0.06
     ^.
    0.06
     若要
    0.06
    SDL
    0.06
    Activations Density 0.031%

    No Known Activations