© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 38461
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash

    The neuron fires on pieces of format‐string syntax (printf/scanf style specifiers like “%d”, “%8.2f”, escape sequences like “\n”, and similar formatting tokens).

    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
    720
    -0.06
    âce
    -0.06
    ПО
    -0.06
    нести
    -0.06
     continuar
    -0.06
    άνει
    -0.06
    AntiForgeryToken
    -0.06
    erase
    -0.06
     BAS
    -0.06
    ejte
    -0.06
    POSITIVE LOGITS
     میان
    0.07
    少年
    0.07
    Contact
    0.06
    FullScreen
    0.06
     lead
    0.06
     Zimbabwe
    0.06
    ming
    0.06
    	sizeof
    0.06
    Limit
    0.06
     Amber
    0.06
    Activations Density 0.000%

    No Known Activations