© 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. 129582
    Prev
    Next
    INDEX
    Explanations

    Legal and official documents

    np_max-act · gemini-2.0-flash

    The neuron activates on legal citation language, such as statute numbers, code sections, chapter and title references.

    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
    كام
    -0.06
    	distance
    -0.06
     cured
    -0.06
     amateurs
    -0.06
    Anywhere
    -0.06
     SES
    -0.05
    osterone
    -0.05
     kou
    -0.05
    ğer
    -0.05
    .sprites
    -0.05
    POSITIVE LOGITS
    -transitional
    0.07
    ються
    0.07
     paired
    0.07
     astounding
    0.06
     Б
    0.06
    -important
    0.06
     _)
    0.06
     MODE
    0.06
     něj
    0.06
     bolster
    0.06
    Activations Density 0.028%

    No Known Activations