© 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
    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. 54258
    Prev
    Next
    INDEX
    Explanations

    Re

    np_max-act · gemini-2.0-flash

    The neuron chiefly activates on the “Re” subtoken (as in category labels like “Recurring,” “Reconciling,” etc.), i.e. it detects the “Re” prefix.

    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
    worm
    -0.07
     export
    -0.07
     Tỉnh
    -0.06
    اعات
    -0.06
    .Order
    -0.06
    -trained
    -0.06
    _ATTACHMENT
    -0.06
    uhan
    -0.06
     tarde
    -0.06
    ethe
    -0.06
    POSITIVE LOGITS
    Re
    0.08
    524
    0.07
     phục
    0.07
     backlash
    0.07
     Re
    0.07
    .Gr
    0.06
    785
    0.06
     Reve
    0.06
     Ref
    0.06
     sequel
    0.06
    Activations Density 0.022%

    No Known Activations