© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 73869
    Prev
    Next
    INDEX
    Explanations

    Pros

    np_max-act · gemini-2.0-flash

    This neuron specifically activates on the string “Pros,” i.e. the prefix “Pros” as it appears in headings like “Pros” or “Prospective.”

    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
    �
    -0.07
    -В
    -0.07
    ,Y
    -0.07
     таб
    -0.06
    _builtin
    -0.06
    只有
    -0.06
    ै,
    -0.06
    Wilson
    -0.06
    เหน
    -0.06
    HeadersHeight
    -0.06
    POSITIVE LOGITS
     composers
    0.06
     Prospect
    0.06
     struggle
    0.06
    grab
    0.06
     pharmacies
    0.06
     Strauss
    0.06
     CD
    0.06
     nào
    0.06
     Access
    0.06
    اوت
    0.06
    Activations Density 0.000%

    No Known Activations