© 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. 7200
    Prev
    Next
    INDEX
    Explanations

    well

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of the phrase “as well.”

    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
    Mono
    -0.08
    	Mono
    -0.07
    ари
    -0.07
    ao
    -0.07
    ria
    -0.07
    cri
    -0.07
    anio
    -0.07
     Ki
    -0.07
    Ki
    -0.06
    ona
    -0.06
    POSITIVE LOGITS
     well
    0.14
    well
    0.10
     also
    0.08
     wouldn
    0.08
     WW
    0.08
     according
    0.07
     better
    0.07
     hơn
    0.07
     underst
    0.07
     Linked
    0.07
    Activations Density 0.024%

    No Known Activations