© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 29992
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron activates on floating‐point numeric literals (decimal numbers) within code.

    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
    ари
    -0.07
    _section
    -0.07
    Έ
    -0.06
     meget
    -0.06
     Galactic
    -0.06
    θε
    -0.06
     있는데
    -0.06
     iVar
    -0.06
    هور
    -0.06
     Alle
    -0.06
    POSITIVE LOGITS
     sai
    0.07
     живот
    0.07
    ๊ก
    0.06
    ::{↵
    0.06
     parted
    0.06
     ga
    0.06
     ={↵
    0.06
     ```↵
    0.06
     Supplements
    0.06
     ترجم
    0.06
    Activations Density 0.071%

    No Known Activations