© 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. 126854
    Prev
    Next
    INDEX
    Explanations

    escape and transition

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of barrier‐crossing processes (e.g. “tunnel,” “escape,” “transition”) in the context of quantum or reaction‐coordinate rate phenomena.

    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
    東
    -0.07
     harga
    -0.07
    rr
    -0.07
    neapolis
    -0.06
    ائ
    -0.06
     privilege
    -0.06
    etti
    -0.06
     intend
    -0.06
    理解
    -0.06
     vegetables
    -0.06
    POSITIVE LOGITS
    ड़क
    0.07
    resp
    0.07
    veedor
    0.07
     полностью
    0.06
    CRE
    0.06
     recommending
    0.06
    (kind
    0.06
     Верхов
    0.06
     slashes
    0.06
    Введите
    0.06
    Activations Density 0.012%

    No Known Activations