© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 30650
    Prev
    Next
    INDEX
    Explanations

    submit

    np_max-act · gemini-2.0-flash

    The neuron activates on form-submission controls, especially the word “submit.”

    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
    公園
    -0.07
     zásad
    -0.06
     JW
    -0.06
    ao
    -0.06
     molt
    -0.06
    SELL
    -0.06
     nk
    -0.06
     OFF
    -0.06
    olecular
    -0.06
     frogs
    -0.06
    POSITIVE LOGITS
     submit
    0.08
     успеш
    0.08
    .subplots
    0.07
     anzeigen
    0.07
     соблюд
    0.07
     submits
    0.07
    -controller
    0.07
     budouc
    0.07
    umb
    0.07
    igaret
    0.07
    Activations Density 0.004%

    No Known Activations