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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 84725
    Prev
    Next
    INDEX
    Explanations

    sports contracts

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of financial terms and transactions—especially contract‐ and deal-related language.

    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
    卢
    -0.07
     escorte
    -0.06
     Desktop
    -0.06
    357
    -0.06
     웨
    -0.06
    شف
    -0.06
     pitcher
    -0.06
     CALC
    -0.06
    Slave
    -0.06
    -java
    -0.06
    POSITIVE LOGITS
     ContentValues
    0.07
     mimetype
    0.07
     jpeg
    0.06
     tüm
    0.06
     Beck
    0.06
    =settings
    0.06
    duplicate
    0.06
    ,,,
    0.06
    requestData
    0.06
    наслідок
    0.06
    Activations Density 0.062%

    No Known Activations