© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 38658
    Prev
    Next
    INDEX
    Explanations

    Technical problems

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric tokens—especially decimal numbers—highlighting measurements or quantitative values in the text.

    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
    .android
    -0.06
    .Att
    -0.06
    Late
    -0.06
     takip
    -0.06
     kang
    -0.06
     Plat
    -0.06
     documentation
    -0.06
    odem
    -0.06
     lust
    -0.06
     bapt
    -0.06
    POSITIVE LOGITS
    스
    0.07
     здійсню
    0.06
    _activate
    0.06
    .putInt
    0.06
    �
    0.06
     بیان
    0.06
    είς
    0.06
    .JPanel
    0.06
     Đề
    0.06
    물을
    0.06
    Activations Density 0.104%

    No Known Activations