© 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. 126597
    Prev
    Next
    INDEX
    Explanations

    restrict

    np_max-act · gemini-2.0-flash

    This neuron detects French phrases about restricting a differential form—specifically occurrences of “restriction de la forme différentielle” (and its variants) to a subspace.

    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
     mascot
    -0.07
     Newman
    -0.06
     �
    -0.06
    Amazon
    -0.06
    Keyword
    -0.06
     Über
    -0.06
     jumlah
    -0.06
     знов
    -0.06
     Dylan
    -0.06
     nud
    -0.06
    POSITIVE LOGITS
    _IDLE
    0.07
    (bean
    0.06
     огранич
    0.06
     AudioManager
    0.06
     court
    0.06
    織
    0.06
    IRR
    0.06
    وسط
    0.06
     -->
↵
    0.06
    _configs
    0.06
    Activations Density 0.005%

    No Known Activations