© 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. 127147
    Prev
    Next
    INDEX
    Explanations

    Human behavior

    np_max-act · gemini-2.0-flash

    This neuron activates on the prompt’s “behavior” indicator, i.e. the token introducing the specific behavior to evaluate.

    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
    Seconds
    -0.07
             ↵
    -0.07
    ('.')↵
    -0.07
    care
    -0.06
     bilingual
    -0.06
    puty
    -0.06
     "}";↵
    -0.06
    .ud
    -0.06
    uard
    -0.06
    	On
    -0.06
    POSITIVE LOGITS
     avantaj
    0.07
    abilidade
    0.07
    ("/{
    0.06
    /theme
    0.06
     деятельности
    0.06
     libr
    0.06
     نسخ
    0.06
    โรงแรม
    0.06
     Hệ
    0.06
    _mail
    0.06
    Activations Density 0.002%

    No Known Activations