© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 90602
    Prev
    Next
    INDEX
    Explanations

    training

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of potty training (references to “potty,” “toilet,” and “training” in that context).

    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
    608
    -0.07
     lyon
    -0.06
     sprav
    -0.06
     PARK
    -0.06
     Kun
    -0.06
     işaret
    -0.06
    çon
    -0.06
     리스트
    -0.06
     tsunami
    -0.06
    信
    -0.06
    POSITIVE LOGITS
    џџ
    0.07
    came
    0.07
    ้เก
    0.07
    -lang
    0.07
    _large
    0.06
    idges
    0.06
    (mut
    0.06
     gew
    0.06
     Behavior
    0.06
     happ
    0.06
    Activations Density 0.007%

    No Known Activations