© 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. 15-RESID-POST-AA
    11. 73506
    Prev
    Next
    INDEX
    Explanations

    numbers and measurements

    np_max-act · gemini-2.0-flash

    Numeric tokens (especially multi-digit numbers, years, and other numeric/statistical values).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     сух
    -0.07
     unser
    -0.07
     Islanders
    -0.07
    nummer
    -0.07
    heimer
    -0.07
    久
    -0.07
    ン�
    -0.07
    ĩa
    -0.06
     Rockefeller
    -0.06
    Element
    -0.06
    POSITIVE LOGITS
     resemble
    0.06
    (KEY
    0.06
    urrect
    0.05
    Clar
    0.05
    ANGES
    0.05
     designing
    0.05
     refers
    0.05
    vfs
    0.05
    <link
    0.05
    .NULL
    0.05
    Activations Density 21.913%

    No Known Activations