© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 13861
    Prev
    Next
    INDEX
    Explanations

    Units of measure

    np_max-act · gemini-2.0-flash

    The neuron detects numeric measurements accompanied by unit abbreviations (e.g. “8 GB,” “23 nm,” “40 Gb,” etc.).

    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
     دهه
    -0.06
    enario
    -0.06
    timestamp
    -0.06
    burn
    -0.06
    namese
    -0.06
    WithError
    -0.06
    erdem
    -0.06
    BoxLayout
    -0.06
    thur
    -0.06
     teamwork
    -0.06
    POSITIVE LOGITS
    _mD
    0.08
     MPS
    0.07
     consisting
    0.07
    اس
    0.07
     financed
    0.06
    CTS
    0.06
     capitals
    0.06
    ,Yes
    0.06
    勒
    0.06
     HIP
    0.06
    Activations Density 0.116%

    No Known Activations