© 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. 88926
    Prev
    Next
    INDEX
    Explanations

    around

    np_max-act · gemini-2.0-flash

    This neuron detects language offering solutions or workarounds—especially phrases like “solution to get around it” or “no matter …” that imply circumventing constraints.

    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
    bib
    -0.06
     mağ
    -0.06
     Только
    -0.06
    ?>
↵
↵
    -0.06
     convinced
    -0.06
    792
    -0.06
     bounce
    -0.06
    zag
    -0.06
    .publish
    -0.06
     hardcore
    -0.06
    POSITIVE LOGITS
     tonnes
    0.07
    	index
    0.07
    堆
    0.06
    очатку
    0.06
     يوم
    0.06
     فرمان
    0.06
    [element
    0.06
    Partner
    0.06
    ueue
    0.06
     اقتصادی
    0.06
    Activations Density 0.001%

    No Known Activations