© 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. 6281
    Prev
    Next
    INDEX
    Explanations

    medical abbreviations

    np_max-act · gemini-2.0-flash

    The neuron activates on short, all‐caps medical acronyms or initialisms (e.g. ICH, SCI, MRI, SAH) in the text.

    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
    cult
    -0.07
    frontend
    -0.07
    /cli
    -0.07
    _BYTE
    -0.07
    .slice
    -0.06
     attract
    -0.06
     ดร
    -0.06
     bird
    -0.06
    arrass
    -0.06
    efeller
    -0.06
    POSITIVE LOGITS
    ιας
    0.06
    ログ
    0.06
     H
    0.06
    Spacer
    0.06
     якого
    0.06
    �
    0.06
     agreeing
    0.06
     Sham
    0.06
    ({↵
    0.05
    (mean
    0.05
    Activations Density 0.047%

    No Known Activations