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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 29509
    Prev
    Next
    INDEX
    Explanations

    layer

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of layering or lamination processes (e.g. “layer,” “laminate,” “multilayer,” “laminating,” “plurality of sheets,” etc.) in technical descriptions.

    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
     centerpiece
    -0.07
     monster
    -0.07
     implant
    -0.07
     syndrome
    -0.06
     pipeline
    -0.06
     stressed
    -0.06
     discussed
    -0.06
     initiative
    -0.06
     investigation
    -0.06
    SELECT
    -0.06
    POSITIVE LOGITS
    ريقة
    0.07
     آرام
    0.07
    ाह
    0.07
     newRow
    0.07
    ея
    0.06
     Detail
    0.06
    Α
    0.06
     재
    0.06
    價
    0.06
     -->
↵
↵
    0.06
    Activations Density 0.019%

    No Known Activations