© 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. 38835
    Prev
    Next
    INDEX
    Explanations

    item product

    np_max-act · gemini-2.0-flash

    The neuron fires on the phrase “this item is” or “this product is,” i.e. when a product is being described with “is.”

    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
    _far
    -0.06
    .layouts
    -0.06
    (Cs
    -0.06
     mieux
    -0.06
    _SUPPLY
    -0.06
    MEMORY
    -0.06
    _history
    -0.06
     Cookies
    -0.06
    _cont
    -0.06
    .safe
    -0.06
    POSITIVE LOGITS
     ورزش
    0.07
    сион
    0.06
    истра
    0.06
     scratched
    0.06
     reminiscent
    0.06
     corros
    0.06
    领
    0.06
    .IN
    0.06
     grandmother
    0.06
    imax
    0.06
    Activations Density 0.014%

    No Known Activations