© 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. 77112
    Prev
    Next
    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash

    The neuron fires most strongly on words that head or introduce defining/relational phrases (e.g. “that” in a relative clause, “name” in “a name to note,” “segment” in “a segment of the population”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    topics related to economic and financial systems.

    oai_token-act-pair · gpt-4o-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
     clearer
    -0.07
    _TV
    -0.07
     Petersburg
    -0.07
    .ToolStripItem
    -0.07
    VarChar
    -0.07
    监听页面
    -0.07
     report
    -0.07
     veins
    -0.06
     assays
    -0.06
     ordinarily
    -0.06
    POSITIVE LOGITS
     Ми
    0.06
    ंप
    0.06
     Hast
    0.06
     sie
    0.06
     �
    0.06
     Infinite
    0.06
    �
    0.06
     پرداخت
    0.06
     انتقال
    0.06
    漂
    0.06
    Activations Density 0.083%

    No Known Activations