© 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. 44968
    Prev
    Next
    INDEX
    Explanations

    learn

    np_max-act · gemini-2.0-flash

    The neuron lights up on words that denote learning or acquiring knowledge (e.g., “learn,” “learning”).

    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
     prohibited
    -0.07
    socket
    -0.07
    ondon
    -0.06
     besie
    -0.06
    كات
    -0.06
     Jackets
    -0.06
     HttpStatus
    -0.06
    ीग
    -0.06
    Ghost
    -0.06
     encompasses
    -0.06
    POSITIVE LOGITS
     learning
    0.16
     learned
    0.13
     learn
    0.13
     Learning
    0.13
    Learning
    0.11
     learnt
    0.11
     Learn
    0.10
    learning
    0.10
    Learn
    0.09
     learner
    0.09
    Activations Density 0.044%

    No Known Activations