© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 6320
    Prev
    Next
    INDEX
    Explanations

    goals and objectives

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of specific financial goals or target amounts (often with accompanying timeframes).

    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
     famed
    -0.07
     rus
    -0.07
     Infos
    -0.06
    ушка
    -0.06
    验证码
    -0.06
    ided
    -0.06
     Ö
    -0.06
     vů
    -0.06
    ewith
    -0.06
     büyük
    -0.06
    POSITIVE LOGITS
    ποι
    0.07
     portfolio
    0.06
     çocuğ
    0.06
     واست
    0.06
     Expense
    0.06
    .Fragment
    0.06
    روع
    0.06
    depend
    0.06
     stalk
    0.06
    ://'
    0.06
    Activations Density 0.039%

    No Known Activations