© 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
    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. 44768
    Prev
    Next
    INDEX
    Explanations

    junction

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of the substring “junction,” including variants like “junctional” or “junctions.”

    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
    BMI
    -0.07
    aimassage
    -0.07
    248
    -0.06
     AI
    -0.06
     Playoff
    -0.06
    193
    -0.06
    Real
    -0.06
    SAVE
    -0.06
     Alv
    -0.06
     Li
    -0.06
    POSITIVE LOGITS
     junction
    0.13
     Junction
    0.10
    UNCTION
    0.09
     mourning
    0.08
    unction
    0.08
    jos
    0.07
    uced
    0.07
    /javascript
    0.07
    ucked
    0.07
    burg
    0.07
    Activations Density 0.003%

    No Known Activations