© 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. 128871
    Prev
    Next
    INDEX
    Explanations

    company names

    np_max-act · gemini-2.0-flash

    This neuron spots named legal case citations (e.g. “Coastal States Gas Corp. v. Department of Energy”) in judicial documents.

    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
    !='
    -0.07
    eta
    -0.07
     observers
    -0.06
    aturdays
    -0.06
     Picker
    -0.06
     обращ
    -0.06
    ewidth
    -0.06
     채용
    -0.06
     поруш
    -0.06
     disemb
    -0.06
    POSITIVE LOGITS
     godt
    0.06
     getPrice
    0.06
    -resolution
    0.06
     مرب
    0.06
    <Unit
    0.06
     dire
    0.06
    -east
    0.06
     �
    0.06
    -region
    0.06
     OrderedDict
    0.05
    Activations Density 0.007%

    No Known Activations