© 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. 42773
    Prev
    Next
    INDEX
    Explanations

    code or configuration

    np_max-act · gemini-2.0-flash

    This neuron fires on quoted parameter or attribute names (strings in quotes) in configuration or code snippets.

    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
     shields
    -0.07
     환
    -0.06
    \Redirect
    -0.06
    enis
    -0.06
     Wr
    -0.06
     spouses
    -0.06
    TES
    -0.06
    丸
    -0.06
     Hansen
    -0.06
     datingsider
    -0.06
    POSITIVE LOGITS
    jang
    0.07
     snag
    0.06
    .isEnabled
    0.06
    .getProperties
    0.06
    ullo
    0.06
    คณะ
    0.06
     accom
    0.06
    Handled
    0.06
     §§
    0.06
    .persistence
    0.06
    Activations Density 0.024%

    No Known Activations