© 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. 38789
    Prev
    Next
    INDEX
    Explanations

    Article text

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on numeric‐statistical economic reporting—i.e. mentions of quantities or percentages (e.g. spending rose X percent in month Y).

    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
     visualization
    -0.06
     personally
    -0.06
     Meeting
    -0.06
    abez
    -0.06
     Chen
    -0.06
    609
    -0.06
     دارد
    -0.06
    229
    -0.06
     shitty
    -0.06
    585
    -0.06
    POSITIVE LOGITS
    (Blueprint
    0.07
     Tolkien
    0.07
    	cont
    0.07
    :Is
    0.07
    \"]
    0.07
    _barang
    0.06
     Д
    0.06
    학년도
    0.06
     apprentices
    0.06
    .Stream
    0.06
    Activations Density 0.009%

    No Known Activations