© 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. 38808
    Prev
    Next
    INDEX
    Explanations

    sense of

    np_max-act · gemini-2.0-flash

    This neuron activates on the word “sense,” particularly when it occurs in definitional or explanatory phrases like “sense of the ….”

    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
     waitress
    -0.07
    ź
    -0.07
    ед
    -0.06
    _RETURNTRANSFER
    -0.06
    GameObjectWithTag
    -0.06
    .AddDays
    -0.06
     station
    -0.06
     '../../
    -0.06
     Superintendent
    -0.06
     crowd
    -0.06
    POSITIVE LOGITS
     Nicolas
    0.06
     очередь
    0.06
     statutes
    0.06
    下载
    0.06
     descriptive
    0.06
    elho
    0.06
     Danish
    0.06
    ublished
    0.06
    MYSQL
    0.06
     стари
    0.06
    Activations Density 0.010%

    No Known Activations