Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 27261
    Prev
    Next
    INDEX
    Explanations

    pairing

    np_max-act · gemini-2.0-flash

    This neuron detects references to superconducting pairing mechanisms (e.g. “BCS,” “Cooper pairs,” “pairing,” “superconduct”).

    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
    otence
    -0.07
     kapı
    -0.06
    requete
    -0.06
     preacher
    -0.06
     καν
    -0.06
     problema
    -0.06
    _Interface
    -0.06
    χής
    -0.06
    rece
    -0.06
    .beginTransaction
    -0.06
    POSITIVE LOGITS
    args
    0.08
    Eth
    0.07
     beginners
    0.07
     inexperienced
    0.07
    enced
    0.06
     naming
    0.06
    Pet
    0.06
    اهرة
    0.06
    Blob
    0.06
     Nam
    0.06
    Activations Density 0.003%

    No Known Activations