© 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. 6024
    Prev
    Next
    INDEX
    Explanations

    /v

    np_max-act · gemini-2.0-flash

    The neuron is specialized to pick out Markdown “badge” tokens—i.e. the parts of URLs and labels in npm/Travis/Coveralls style image‐shields.

    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
    REET
    -0.06
     Рос
    -0.06
     precis
    -0.06
     المخت
    -0.06
     filmm
    -0.06
    ниці
    -0.06
    bear
    -0.06
    monitor
    -0.06
    .selected
    -0.05
     projet
    -0.05
    POSITIVE LOGITS
    olithic
    0.07
    251
    0.06
     consenting
    0.06
    endTime
    0.06
     Evolution
    0.06
     Washer
    0.06
     Steve
    0.06
     Salesforce
    0.06
    lectric
    0.06
    PED
    0.06
    Activations Density 0.002%

    No Known Activations