© 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. 57522
    Prev
    Next
    INDEX
    Explanations

    business documents

    np_max-act · gemini-2.0-flash

    The neuron detects the marketing call-to-action phrase centered on “IBM OpenPages can …,” i.e. mentions of the product name “IBM OpenPages” followed by “can.”

    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
     Jeho
    -0.07
     ^(
    -0.07
     suppl
    -0.06
     sizin
    -0.06
     stripslashes
    -0.06
    apses
    -0.06
    .datasets
    -0.06
    RFC
    -0.06
    眼睛
    -0.06
    /******************************************************************************↵
    -0.06
    POSITIVE LOGITS
    láda
    0.07
    .isVisible
    0.06
    (parse
    0.06
     typeName
    0.06
     Chiến
    0.06
    ρκ
    0.06
    seconds
    0.06
    .setUser
    0.06
     ситуации
    0.06
     Freedom
    0.06
    Activations Density 0.054%

    No Known Activations