© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 65220
    Prev
    Next
    INDEX
    Explanations

    technical topics

    np_max-act · gemini-2.0-flash

    The neuron lights up on rare or unusual word‐piece tokens—especially parts of proper names, technical terms, or foreign/less common words.

    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
    τικα
    -0.06
    ulls
    -0.06
    places
    -0.06
    oly
    -0.06
     swaps
    -0.06
    idence
    -0.06
     متفاوت
    -0.06
     pressured
    -0.06
     індив
    -0.06
    portfolio
    -0.06
    POSITIVE LOGITS
     Hero
    0.07
     CLR
    0.06
    σι
    0.06
     Word
    0.06
     avoided
    0.06
     Hàng
    0.06
    xFC
    0.05
    lop
    0.05
     Large
    0.05
    nej
    0.05
    Activations Density 0.136%

    No Known Activations