© 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. 43481
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    This neuron is essentially inactive and does not respond to any tokens—it does not detect any specific pattern.

    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
    Israeli
    -0.07
    Не
    -0.07
     navigation
    -0.07
    -payment
    -0.06
    Db
    -0.06
    买
    -0.06
    Trail
    -0.06
    ■
    -0.06
     бет
    -0.06
    _lists
    -0.06
    POSITIVE LOGITS
     spotify
    0.07
     stature
    0.07
    .AutoField
    0.07
    んで
    0.06
    Coroutine
    0.06
     OC
    0.06
     outdoors
    0.06
    俊
    0.06
     deviceId
    0.06
     dễ
    0.06
    Activations Density 0.010%

    No Known Activations