© 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. 57050
    Prev
    Next
    INDEX
    Explanations

    adverbs of good fortune

    np_max-act · gemini-2.0-flash

    The neuron detects positive-transition adverbs (e.g. “Fortunately,” “Thankfully,” “Luckily,” etc.) that signal relief or a favorable turn in the discourse.

    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
    Concat
    -0.07
    (GUI
    -0.07
     ifade
    -0.06
    吐
    -0.06
     contested
    -0.06
    _average
    -0.06
    müştür
    -0.06
    서비스
    -0.06
    .SerializedName
    -0.06
     olursa
    -0.06
    POSITIVE LOGITS
     Fortunately
    0.10
    Fortunately
    0.08
     Thankfully
    0.07
     Luckily
    0.07
     luckily
    0.07
    Luckily
    0.06
     theolog
    0.06
     Crimes
    0.06
    _reporting
    0.06
     Prepare
    0.06
    Activations Density 0.010%

    No Known Activations