© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 44215
    Prev
    Next
    INDEX
    Explanations

    under

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on the word “under” when it’s used to introduce experimental or condition settings.

    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
    .AllArgsConstructor
    -0.06
    iolet
    -0.06
    จะต
    -0.06
     analý
    -0.06
    illis
    -0.06
     dapat
    -0.06
     Ferrari
    -0.06
     duas
    -0.06
     twins
    -0.06
     Gabriel
    -0.06
    POSITIVE LOGITS
     <
    0.07
     lä
    0.06
     under
    0.06
     deer
    0.06
    bb
    0.06
     bitch
    0.06
     thuốc
    0.06
     robert
    0.06
     bb
    0.06
     rex
    0.06
    Activations Density 0.009%

    No Known Activations