© 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
    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. 110335
    Prev
    Next
    INDEX
    Explanations

    learning

    np_max-act · gemini-2.0-flash

    The neuron flags technical AI and machine-learning terms and jargon (e.g. “AI,” “machine,” “learning,” “language,” “vision,” “transformer”).

    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
     analsex
    -0.06
     Kotlin
    -0.06
    _AHB
    -0.06
    Nhap
    -0.06
     neuken
    -0.06
    HANDLE
    -0.06
    elfth
    -0.06
     Buttons
    -0.06
     امروز
    -0.06
     Bags
    -0.06
    POSITIVE LOGITS
     benches
    0.07
    ucceed
    0.07
     prosecutions
    0.06
    ours
    0.06
    iless
    0.06
     lay
    0.06
    storage
    0.06
     persist
    0.06
     difficulties
    0.06
     visited
    0.06
    Activations Density 0.024%

    No Known Activations