© 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. 109140
    Prev
    Next
    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash

    The neuron fires on common English “filler” tokens used to introduce explanations (e.g. “there,” “is,” “a,” “also,” “if”).

    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
    -first
    -0.07
    estring
    -0.06
     Sher
    -0.06
    ीक
    -0.06
    िवर
    -0.06
    Patient
    -0.06
     surged
    -0.05
     Cartesian
    -0.05
    ombies
    -0.05
    if
    -0.05
    POSITIVE LOGITS
    ่างก
    0.07
    \↵
    0.07
     Transcript
    0.07
     چیست
    0.07
    พย
    0.07
    ımı
    0.06
    asında
    0.06
    вод
    0.06
     цьому
    0.06
     chtě
    0.06
    Activations Density 0.038%

    No Known Activations