© 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. 29516
    Prev
    Next
    INDEX
    Explanations

    Agriculture and resources

    np_max-act · gemini-2.0-flash

    discussions about the domestication and significance of livestock, specifically cattle.

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

    The neuron detects nouns that list practical uses or benefits (e.g., “food,” “clothing,” “companionship,” “tasks”).

    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
     nameof
    -0.07
    elor
    -0.07
     ký
    -0.07
     seal
    -0.06
     віднос
    -0.06
     Wochen
    -0.06
     '#'
    -0.06
     between
    -0.06
     sequences
    -0.06
     Hashtable
    -0.06
    POSITIVE LOGITS
    ++)
    0.06
     üzerinden
    0.06
     留
    0.06
    &P
    0.06
     eighty
    0.06
    -fashioned
    0.06
    СО
    0.06
    اصيل
    0.06
    _makeConstraints
    0.06
     reprint
    0.06
    Activations Density 0.041%

    No Known Activations