© 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. 56359
    Prev
    Next
    INDEX
    Explanations

    friendly

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the adjective “friendly” (e.g. in “user-friendly,” “customer-friendly,” “mobile-friendly”), flagging hyphenated descriptors that denote ease of use or accessibility.

    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
     déc
    -0.07
     cubes
    -0.06
     bize
    -0.06
    -volume
    -0.06
     deco
    -0.06
     Backup
    -0.06
    ‌باشد
    -0.06
     scé
    -0.06
    	    
    -0.06
    年龄
    -0.06
    POSITIVE LOGITS
    -friendly
    0.12
     friendly
    0.11
    riendly
    0.09
    friendly
    0.09
     Trey
    0.08
     Friendly
    0.08
    innerText
    0.08
     brid
    0.07
    利
    0.07
    ён
    0.07
    Activations Density 0.007%

    No Known Activations