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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 6723
    Prev
    Next
    INDEX
    Explanations

    fairy tales

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on the Russian fairy‐tale opening phrase “Жила-была” (the “Once upon a time” formula).

    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
    .fb
    -0.07
    _De
    -0.06
     kidn
    -0.06
    _ud
    -0.06
    geber
    -0.06
     دار
    -0.06
    .GetName
    -0.06
    _documents
    -0.06
     URLRequest
    -0.06
    imb
    -0.06
    POSITIVE LOGITS
     enduring
    0.06
     direkt
    0.06
    Copyright
    0.06
     Flowers
    0.06
     cle
    0.06
     {↵↵↵↵
    0.06
    直接
    0.06
    asics
    0.06
     sliding
    0.06
     cach
    0.06
    Activations Density 0.146%

    No Known Activations