© 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. 128431
    Prev
    Next
    INDEX
    Explanations

    anti

    np_max-act · gemini-2.0-flash

    chemical compounds with specific structural characteristics and their applications in various industries.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron responds to IUPAC‐style chemical names—multi‐part names with numbers, hyphens, and parenthetical substituents.

    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
     Pru
    -0.07
     borne
    -0.07
    -mounted
    -0.07
     Lav
    -0.07
    aping
    -0.07
    chedulers
    -0.06
    IsNull
    -0.06
     mData
    -0.06
    leyen
    -0.06
    Players
    -0.06
    POSITIVE LOGITS
     浙江
    0.06
     Huge
    0.06
     fauna
    0.06
    敌
    0.06
    ้ย
    0.06
    (audio
    0.06
    male
    0.06
     During
    0.06
    ######↵
    0.05
    敵
    0.05
    Activations Density 0.005%

    No Known Activations