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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 57695
    Prev
    Next
    INDEX
    Explanations

    insufficiency

    np_max-act · gemini-2.0-flash

    The neuron detects language expressing limitations or inadequacy (critique) in methods or models.

    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
    	msg
    -0.06
     könnte
    -0.06
     мел
    -0.06
    Female
    -0.06
     порядок
    -0.06
     přímo
    -0.06
    以来
    -0.06
     Duchess
    -0.06
    -INF
    -0.06
     twice
    -0.06
    POSITIVE LOGITS
    original
    0.06
     campaigning
    0.06
    保险
    0.06
     ingres
    0.06
    aviors
    0.06
    ียญ
    0.06
     getResource
    0.06
     Ör
    0.06
     ORIGINAL
    0.06
    είου
    0.06
    Activations Density 0.060%

    No Known Activations