© 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. 13618
    Prev
    Next
    INDEX
    Explanations

    code, boolean logic

    np_max-act · gemini-2.0-flash

    This neuron fires on C++ member‐function definitions or calls named “show” with a boolean parameter (e.g. show(bool bShow)).

    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
    -independent
    -0.07
    арам
    -0.06
    ceans
    -0.06
     drone
    -0.06
    �
    -0.06
    ковые
    -0.06
     signIn
    -0.06
    .gradle
    -0.06
     ні
    -0.06
    iaux
    -0.06
    POSITIVE LOGITS
     unilateral
    0.07
     місцев
    0.07
    <Article
    0.06
    "]=>
    0.06
     będzie
    0.06
     alors
    0.06
     marching
    0.06
     Side
    0.06
    ledger
    0.06
    '>
↵
    0.06
    Activations Density 0.004%

    No Known Activations