© 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. 126403
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    The neuron activates primarily on decimal numeric tokens (floating‐point numbers).

    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
     Displays
    -0.06
    _bg
    -0.06
     Valle
    -0.06
     створення
    -0.06
    .card
    -0.06
    dealer
    -0.06
    asper
    -0.06
     Fulton
    -0.06
     Dust
    -0.06
    ιστη
    -0.06
    POSITIVE LOGITS
    aleza
    0.06
    problems
    0.06
    IRM
    0.06
     accompanying
    0.06
     initiatives
    0.06
     širo
    0.06
    ится
    0.06
     ratings
    0.06
     supposed
    0.06
    replacement
    0.06
    Activations Density 0.000%

    No Known Activations