© 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. 12291
    Prev
    Next
    INDEX
    Explanations

    percentages

    np_max-act · gemini-2.0-flash

    references to maternal mortality and related health issues in the context of developing countries.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron is tuned to detect numeric expressions—particularly decimals, percentages, and other quantitative tokens.

    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
    naments
    -0.06
    „
    -0.06
    شف
    -0.06
     somewhat
    -0.06
    prov
    -0.06
     lazım
    -0.06
    存
    -0.06
    ид
    -0.06
     pw
    -0.06
    buscar
    -0.06
    POSITIVE LOGITS
     recovered
    0.07
     Military
    0.07
     Portland
    0.07
    _COMMAND
    0.07
    ={},
    0.06
     BusinessException
    0.06
    없이
    0.06
     secular
    0.06
     home
    0.06
     episodes
    0.06
    Activations Density 0.057%

    No Known Activations