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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 109122
    Prev
    Next
    INDEX
    Explanations

    Non-English languages

    np_max-act · gemini-2.0-flash

    The neuron responds most strongly to capitalized tokens, i.e. proper names and other named entities.

    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
     Trade
    -0.08
    Italic
    -0.07
    _STANDARD
    -0.07
    itsu
    -0.07
     Eug
    -0.07
    itest
    -0.06
     Conserv
    -0.06
    SF
    -0.06
     Fahrenheit
    -0.06
    REN
    -0.06
    POSITIVE LOGITS
     ha
    0.09
     have
    0.08
     has
    0.08
     حيث
    0.08
    __(↵
    0.07
    	    	
    0.07
     vai
    0.07
    �
    0.07
     estão
    0.07
    	    
    0.07
    Activations Density 0.037%

    No Known Activations