© 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. 6194
    Prev
    Next
    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash

    general inquiries about the AI's capabilities and functionalities.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron activates on the common self-referential disclaimer phrase (“As an AI language model…”) that the assistant uses to introduce its identity or limitations.

    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
     Bulld
    -0.07
    .Parcelable
    -0.07
     Perry
    -0.07
    ESCO
    -0.06
    تيار
    -0.06
    érieur
    -0.06
     br
    -0.06
    -bedroom
    -0.06
     FOX
    -0.06
     decryption
    -0.06
    POSITIVE LOGITS
     �
    0.07
    rette
    0.06
    Bug
    0.06
     yere
    0.06
    ("/:
    0.06
     Doğ
    0.06
    	array
    0.06
     SECOND
    0.06
     viel
    0.06
     xlink
    0.06
    Activations Density 0.062%

    No Known Activations