© 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. 9069
    Prev
    Next
    INDEX
    Explanations

    action video games

    np_max-act · gemini-2.0-flash

    This neuron responds to promotional or hype adjectives and other marketing-style descriptors (e.g. “dynamic,” “ever-changing,” “breathtaking,” “definitive,” etc.).

    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
     miracles
    -0.06
     Louis
    -0.06
     Doe
    -0.06
     CS
    -0.06
     کوت
    -0.06
     rins
    -0.06
     Europ
    -0.06
    option
    -0.06
    .setChecked
    -0.06
    ")),
    -0.06
    POSITIVE LOGITS
     colore
    0.07
    /o
    0.07
     Military
    0.06
     fueron
    0.06
     Spinner
    0.06
     rpt
    0.06
     satu
    0.06
    链
    0.06
     laboratory
    0.06
     Highlight
    0.06
    Activations Density 0.028%

    No Known Activations