© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 110289
    Prev
    Next
    INDEX
    Explanations

    alphanumeric characters and numbers

    np_max-act · gemini-2.0-flash

    The neuron activates on digit characters (numeric ranges or digit shorthand like “0-9” or “\d”) in regular‐expression contexts.

    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
     cleaner
    -0.06
    .guild
    -0.06
     playbook
    -0.06
    fullscreen
    -0.06
    �
    -0.06
    .ServletException
    -0.06
     giai
    -0.06
    นาด
    -0.06
    オ
    -0.06
    nesday
    -0.06
    POSITIVE LOGITS
     proclamation
    0.07
    Adjusted
    0.07
    Comic
    0.07
     stránky
    0.06
     concentrating
    0.06
    (cb
    0.06
     skup
    0.06
     newPath
    0.06
     accountability
    0.06
     документа
    0.06
    Activations Density 0.011%

    No Known Activations