© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 58568
    Prev
    Next
    INDEX
    Explanations

    condiments and spreads

    np_max-act · gemini-2.0-flash

    The neuron activates on names of common sandwich or hot-dog condiments and sauces.

    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
    録
    -0.08
     Focus
    -0.07
    Activity
    -0.07
     прит
    -0.06
    联网
    -0.06
     některé
    -0.06
    _rb
    -0.06
     limbs
    -0.06
     Activity
    -0.06
    。。
    -0.06
    POSITIVE LOGITS
     mustard
    0.10
    -pe
    0.07
    ์ฟ
    0.07
    Soap
    0.07
    etchup
    0.07
    modifiers
    0.07
    ège
    0.07
     Cheese
    0.06
     Replace
    0.06
     repairing
    0.06
    Activations Density 0.003%

    No Known Activations