© 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. 124817
    Prev
    Next
    INDEX
    Explanations

    carnivores

    np_max-act · gemini-2.0-flash

    This neuron detects animal dietary terms—specifically words containing the “-ivor”/“-ivore” morpheme indicating feeding type (e.g., herbivore, carnivore, omnivore).

    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
     Scrap
    -0.06
     validationResult
    -0.06
     architectural
    -0.06
     skating
    -0.06
    qli
    -0.06
     startTime
    -0.06
    -current
    -0.06
     Fritz
    -0.06
    /send
    -0.06
     RELEASE
    -0.06
    POSITIVE LOGITS
     někdy
    0.07
     carniv
    0.07
     budete
    0.06
    cran
    0.06
     Cah
    0.06
     entra
    0.06
    еров
    0.06
     craving
    0.06
    τός
    0.06
    йом
    0.06
    Activations Density 0.004%

    No Known Activations