© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 89165
    Prev
    Next
    INDEX
    Explanations

    Stop words

    np_max-act · gemini-2.0-flash

    This neuron responds to language about social justice and advocacy—terms related to the rights, empowerment, and representation of marginalized or disadvantaged groups.

    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
     meal
    -0.07
     quanto
    -0.07
     card
    -0.07
    _IE
    -0.07
    ,!
    -0.06
     strongly
    -0.06
    uren
    -0.06
    _sleep
    -0.06
     throat
    -0.06
     camper
    -0.06
    POSITIVE LOGITS
     discriminate
    0.07
     Св
    0.07
    ğında
    0.07
     Ав
    0.07
     돈
    0.06
     Hicks
    0.06
     NSMutableDictionary
    0.06
     dismal
    0.06
     distinctly
    0.06
    ___
    0.06
    Activations Density 0.056%

    No Known Activations