Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 125323
    Prev
    Next
    INDEX
    Explanations

    contend

    np_max-act · gemini-2.0-flash

    This neuron detects legal-pleading verbs expressing a party’s assertion or contention (e.g., “contend,” “contending,” “contends”).

    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
    Amy
    -0.07
     там
    -0.07
    ju
    -0.07
    ku
    -0.07
    微笑
    -0.06
     глаза
    -0.06
    _death
    -0.06
     Pregnancy
    -0.06
    .large
    -0.06
     Winter
    -0.06
    POSITIVE LOGITS
     contend
    0.10
     contends
    0.08
     بتن
    0.07
    تون
    0.07
    ンズ
    0.07
    rell
    0.07
     contenders
    0.07
     contention
    0.07
     pertinent
    0.07
     Holden
    0.07
    Activations Density 0.003%

    No Known Activations