© 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. 44613
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on numeric tokens (dates, ages, years, measurements, 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
     PTSD
    -0.07
    Kit
    -0.07
    ворю
    -0.07
    雲
    -0.06
    วงศ
    -0.06
    鸟
    -0.06
    707
    -0.06
    Mongo
    -0.06
    _Metadata
    -0.06
    FragmentManager
    -0.06
    POSITIVE LOGITS
     �
    0.06
     bem
    0.06
     серьез
    0.06
     workflow
    0.06
     효
    0.06
    َ
    0.06
     bunun
    0.06
    收
    0.06
    /k
    0.06
    ेम
    0.06
    Activations Density 0.331%

    No Known Activations