© 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. 41267
    Prev
    Next
    INDEX
    Explanations

    chemical starting materials

    np_max-act · gemini-2.0-flash

    The neuron activates on phrasing that labels a compound as a synthesis precursor—e.g. calling it an “intermediate” or “starting material.”

    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
    Ny
    -0.08
    Construct
    -0.07
     ▼
    -0.07
     cancer
    -0.06
     toàn
    -0.06
     Restoration
    -0.06
    Monitoring
    -0.06
     Manor
    -0.06
    dis
    -0.06
    MDB
    -0.06
    POSITIVE LOGITS
    мерик
    0.06
    ispers
    0.06
    usra
    0.06
     θε
    0.06
     Mass
    0.05
     Allah
    0.05
     signup
    0.05
    -selling
    0.05
     referrals
    0.05
     stump
    0.05
    Activations Density 0.009%

    No Known Activations