© 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. 9454
    Prev
    Next
    INDEX
    Explanations

    Terms and policies

    np_max-act · gemini-2.0-flash

    This neuron fires on section titles or headings containing the phrase “Terms of Service” (or close variants like “Terms of Use”).

    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
    軽
    -0.07
     prophets
    -0.07
     ضر
    -0.07
    agn
    -0.06
    aycast
    -0.06
           ↵
    -0.06
    ams
    -0.06
    手に
    -0.06
     производ
    -0.06
    Ậ
    -0.06
    POSITIVE LOGITS
     Xunit
    0.07
     disappointed
    0.06
     ifade
    0.06
    ")
↵
    0.06
    ArgumentNullException
    0.06
     hunted
    0.06
     educate
    0.05
    ètres
    0.05
     overarching
    0.05
    smarty
    0.05
    Activations Density 0.007%

    No Known Activations