© 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. 90609
    Prev
    Next
    INDEX
    Explanations

    contract extensions

    np_max-act · gemini-2.0-flash

    The neuron detects language referring to optional extensions in contracts (e.g., “option to extend,” “option for a two-year extension,” etc.).

    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
    INU
    -0.07
     پرد
    -0.07
     orthodox
    -0.07
    ingu
    -0.06
    .End
    -0.06
     leicht
    -0.06
    raz
    -0.06
    UK
    -0.06
    Student
    -0.06
    	from
    -0.06
    POSITIVE LOGITS
    _CURRENT
    0.07
     celle
    0.06
    لوب
    0.06
    .sources
    0.06
    typeparam
    0.06
    ندگی
    0.06
     Ferry
    0.06
     вет
    0.06
    (agent
    0.06
    天堂
    0.06
    Activations Density 0.006%

    No Known Activations