© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 129684
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    This neuron detects numeric tokens written as decimal numbers (floating‐point values).

    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
    DEFINED
    -0.07
    ativo
    -0.06
    uellen
    -0.06
    othermal
    -0.06
    沈
    -0.06
     ویرایش
    -0.06
    懂
    -0.06
    XXXX
    -0.06
    號
    -0.06
    ๊ก
    -0.06
    POSITIVE LOGITS
    =$(
    0.07
    [string
    0.07
    租
    0.07
     kdyby
    0.07
     ebooks
    0.06
     Ere
    0.06
     Tai
    0.06
     ''.
    0.06
     faiz
    0.06
    [src
    0.06
    Activations Density 0.028%

    No Known Activations