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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 129761
    Prev
    Next
    INDEX
    Explanations

    oil

    np_max-act · gemini-2.0-flash

    This neuron activates on recipe ingredient listings, especially measured food items (e.g. quantities with units and ingredient names).

    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
    leshoot
    -0.07
    signIn
    -0.07
    heads
    -0.07
    _PACKAGE
    -0.07
     payments
    -0.07
     toán
    -0.07
    -device
    -0.07
     П
    -0.06
    463
    -0.06
    orgot
    -0.06
    POSITIVE LOGITS
     McM
    0.06
    mland
    0.06
     Teh
    0.06
     doktor
    0.06
    dart
    0.05
     melod
    0.05
    .Fatalf
    0.05
     كثير
    0.05
     PodsDummy
    0.05
    Cursor
    0.05
    Activations Density 0.010%

    No Known Activations