© 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 EvalsExportsinterp-engineNEWAPI 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. 58182
    Prev
    Next
    INDEX
    Explanations

    inventions

    np_max-act · gemini-2.0-flash

    This neuron fires on the main subject-matter noun phrase (the invention’s title) in the “Field of the Invention” header, e.g. “printed circuit board,” “ion sensor,” “switching regulator,” 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
    orders
    -0.07
    .cum
    -0.07
    ioms
    -0.06
     prejudice
    -0.06
    ellers
    -0.06
     scrutiny
    -0.06
    etermined
    -0.06
    urry
    -0.06
     survival
    -0.06
    _need
    -0.06
    POSITIVE LOGITS
     Flyers
    0.07
    dal
    0.06
    /Header
    0.06
    oğ
    0.06
    网刊
    0.06
    нула
    0.06
     Getter
    0.06
     Hulk
    0.06
     така
    0.06
    upportInitialize
    0.06
    Activations Density 0.025%

    No Known Activations