© 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. 124951
    Prev
    Next
    INDEX
    Explanations

    scientific classification descriptions

    np_max-act · gemini-2.0-flash

    references to specific proteins and their biological roles in health and disease.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects phrases stating that a biological entity “is a member of” or “belongs to” a particular family or group.

    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
     Angebot
    -0.07
    िथ
    -0.06
     serde
    -0.06
     LD
    -0.06
    аря
    -0.06
    Utc
    -0.06
     Narrative
    -0.06
     operational
    -0.06
    оятель
    -0.06
     Katy
    -0.06
    POSITIVE LOGITS
    ітет
    0.06
    _Font
    0.06
     issu
    0.06
     klar
    0.06
    inizin
    0.06
     हट
    0.06
     ranger
    0.06
     घटन
    0.06
     getClass
    0.06
    нения
    0.06
    Activations Density 0.008%

    No Known Activations