© 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. 12229
    Prev
    Next
    INDEX
    Explanations

    Vitamin D3

    np_max-act · gemini-2.0-flash

    The neuron fires on the numeric part of supplement or vitamin subtype labels (e.g. the “3” in “D3” or the “2” in “K2”).

    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
    position
    -0.08
    描述
    -0.07
     수정
    -0.07
    ried
    -0.07
    warf
    -0.07
    face
    -0.07
    -legged
    -0.06
    fol
    -0.06
     supern
    -0.06
     Dagger
    -0.06
    POSITIVE LOGITS
    .assertIn
    0.06
     ศ
    0.06
     จำก
    0.06
     Cs
    0.06
     araç
    0.06
    ۱۷
    0.06
     postgres
    0.06
    اقتص
    0.06
    กร
    0.06
     DPR
    0.06
    Activations Density 0.000%

    No Known Activations