© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 129855
    Prev
    Next
    INDEX
    Explanations

    Age

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric age specifications (e.g. “10 Year Old,” “18 Year Old”) in whisky descriptions.

    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
    找到
    -0.07
    ardin
    -0.07
    -dominated
    -0.06
    ]<=
    -0.06
    calcul
    -0.06
    .opts
    -0.06
    нів
    -0.06
     お
    -0.06
     thôi
    -0.06
    .ToShort
    -0.06
    POSITIVE LOGITS
     ether
    0.07
     Mons
    0.07
     iCloud
    0.07
    (QObject
    0.06
     Cloud
    0.06
     Siri
    0.06
     arose
    0.06
    43
    0.06
     cdr
    0.06
    สถานท
    0.06
    Activations Density 0.002%

    No Known Activations