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

    Neuronpedia

    Jacobian LensNEW
    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. 38573
    Prev
    Next
    INDEX
    Explanations

    enjoy

    np_max-act · gemini-2.0-flash

    This neuron fires on occurrences of the verb “enjoy” (and its inflected forms).

    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
     hacked
    -0.08
     cave
    -0.08
     creed
    -0.07
     certificate
    -0.07
     pure
    -0.07
     call
    -0.07
     laptop
    -0.07
     kite
    -0.07
    _case
    -0.07
     Creed
    -0.07
    POSITIVE LOGITS
     enjoyed
    0.13
     enjoyment
    0.12
     enjoying
    0.11
     enjoy
    0.10
    Enjoy
    0.09
     enjoyable
    0.09
     Enjoy
    0.09
    joy
    0.08
    JO
    0.08
    อย
    0.07
    Activations Density 0.019%

    No Known Activations