© 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. 7258
    Prev
    Next
    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash

    This neuron detects the “2” in Pacific Reporter (2d) citations—that is, it lights up on P. 2d case‐report citations.

    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
     kotlinx
    -0.06
    ")]
    -0.06
     monastery
    -0.06
     ακ
    -0.06
     KD
    -0.06
     died
    -0.06
    .movies
    -0.06
    .Rect
    -0.06
    JD
    -0.06
    rites
    -0.06
    POSITIVE LOGITS
    .gmail
    0.07
     turkey
    0.07
    India
    0.07
     сог
    0.06
    ='$
    0.06
    طقة
    0.06
    _Type
    0.06
     رف
    0.06
    FormData
    0.06
     ****************
    0.06
    Activations Density 0.000%

    No Known Activations