© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 13014
    Prev
    Next
    INDEX
    Explanations

    easily

    np_max-act · gemini-2.0-flash

    The neuron activates on the adverb “easily,” flagging expressions that indicate something can be done with ease.

    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
     Prize
    -0.07
     mužů
    -0.07
    [count
    -0.07
     revived
    -0.07
    víc
    -0.07
     submar
    -0.06
    .richTextBox
    -0.06
     Richards
    -0.06
     ніколи
    -0.06
     provozu
    -0.06
    POSITIVE LOGITS
     easily
    0.19
     Easily
    0.12
     easy
    0.11
     Easy
    0.09
     effortlessly
    0.09
    易
    0.08
     readily
    0.07
     easier
    0.07
    easy
    0.07
     facile
    0.07
    Activations Density 0.041%

    No Known Activations