Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 126430
    Prev
    Next
    INDEX
    Explanations

    applications

    np_max-act · gemini-2.0-flash

    The neuron activates on the word “application” (including its plural and section‐heading forms) in the text.

    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
     JSON
    -0.07
    ering
    -0.07
    .Visibility
    -0.06
     restroom
    -0.06
    .Position
    -0.06
    Plan
    -0.06
    _editor
    -0.06
    Reuters
    -0.06
     labeling
    -0.06
    sku
    -0.06
    POSITIVE LOGITS
     applications
    0.08
     Applications
    0.08
     application
    0.07
    reamble
    0.06
     الأخ
    0.06
    phi
    0.06
    ギ
    0.06
    applications
    0.06
    steen
    0.06
     dụng
    0.06
    Activations Density 0.040%

    No Known Activations