© 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. 57095
    Prev
    Next
    INDEX
    Explanations

    semicolon

    np_max-act · gemini-2.0-flash

    HTML and CSS code related to user interface elements, particularly focusing on interactive components like chatbots or messaging apps.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron appears to remain inactive and does not detect any particular token or pattern.

    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
    445
    -0.07
    ерше
    -0.07
     infrared
    -0.07
     existence
    -0.07
    辛
    -0.06
     survives
    -0.06
    ID
    -0.06
     sticker
    -0.06
    UMENT
    -0.06
     İlk
    -0.06
    POSITIVE LOGITS
    だな
    0.07
     на
    0.07
    	active
    0.07
     питания
    0.07
     Yani
    0.07
    implements
    0.07
    ->__
    0.06
    jších
    0.06
    (COLOR
    0.06
    운동
    0.06
    Activations Density 0.006%

    No Known Activations