© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 42745
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash

    The neuron responds to the angle-bracketed generic type syntax (e.g. “<T>”, “List<Event>”, “System.Collections.Generic…IList<Event>”).

    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
    IDGET
    -0.07
    apse
    -0.06
    太阳城
    -0.06
     cate
    -0.06
    _cards
    -0.06
    _literals
    -0.06
     drunk
    -0.06
    03
    -0.06
     cloth
    -0.06
    둘
    -0.06
    POSITIVE LOGITS
     Doctors
    0.07
    モデル
    0.07
     veri
    0.06
    health
    0.06
     معن
    0.06
     بشكل
    0.06
     Ank
    0.06
     پنج
    0.06
     inequalities
    0.06
    .getActive
    0.06
    Activations Density 0.011%

    No Known Activations