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

    Neuronpedia

    Jacobian LensNEW
    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. 56636
    Prev
    Next
    INDEX
    Explanations

    puns

    np_max-act · gemini-2.0-flash

    This neuron fires on little animal- or “furry”-style onomatopoeic syllables (e.g. paw(s), me-ow, fur, 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
     pazar
    -0.07
    ’t
    -0.06
    -vis
    -0.06
     Printed
    -0.06
     replaced
    -0.06
     Battles
    -0.06
    urst
    -0.06
    “But
    -0.06
     Geb
    -0.06
     Bid
    -0.06
    POSITIVE LOGITS
     Momentum
    0.08
    選
    0.08
    CppMethod
    0.07
    FIELDS
    0.06
     ply
    0.06
    repid
    0.06
    зи
    0.06
    omentum
    0.06
    margin
    0.06
     langs
    0.06
    Activations Density 0.004%

    No Known Activations