© 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. 89186
    Prev
    Next
    INDEX
    Explanations

    equals sign

    np_max-act · gemini-2.0-flash

    The neuron is keyed to floating‐point numerals—i.e. decimal numbers—wherever they appear 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
     contingency
    -0.07
    ozem
    -0.07
    洋
    -0.06
     Lu
    -0.06
     Sy
    -0.06
    "@
    -0.06
     Bran
    -0.06
    veillance
    -0.06
    radi
    -0.06
     měla
    -0.06
    POSITIVE LOGITS
    情况
    0.07
    츠
    0.07
     تفاوت
    0.07
    aştır
    0.06
    ửa
    0.06
    ('=
    0.06
    'options
    0.06
     Galaxy
    0.06
     GLint
    0.06
    صه
    0.06
    Activations Density 0.038%

    No Known Activations