© 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. 13399
    Prev
    Next
    INDEX
    Explanations

    legal documents/court records

    np_max-act · gemini-2.0-flash

    The neuron activates on the ordinal word naming the appellate district (e.g. “Fourth,” “Fifth”) in the court heading.

    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
     Explore
    -0.07
     Vis
    -0.07
    agascar
    -0.07
     Zambia
    -0.06
     Gim
    -0.06
     Analyst
    -0.06
     Corinthians
    -0.06
     precursor
    -0.06
    Vis
    -0.06
    	FILE
    -0.06
    POSITIVE LOGITS
     zdravot
    0.07
     twisted
    0.07
    .Slf
    0.07
     lessen
    0.06
    '"
    0.06
    cling
    0.06
    createElement
    0.06
     طول
    0.06
     xuống
    0.06
     Tennessee
    0.06
    Activations Density 0.000%

    No Known Activations