© 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. 110235
    Prev
    Next
    INDEX
    Explanations

    Period

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens related to money and fundraising (e.g. donations, fundraising pages, donors, funds).

    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
     spam
    -0.07
    _Select
    -0.07
     mixed
    -0.06
    ۳
    -0.06
     mantra
    -0.06
    itele
    -0.06
    greens
    -0.06
     suspended
    -0.06
     racist
    -0.06
     Sanders
    -0.06
    POSITIVE LOGITS
     toán
    0.07
     профилакти
    0.07
     odpowied
    0.07
     {(
    0.06
     pří
    0.06
    =((
    0.06
    )obj
    0.06
     optim
    0.06
    \:
    0.06
     recurrence
    0.06
    Activations Density 0.100%

    No Known Activations