© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 68417
    Prev
    Next
    INDEX
    Explanations

    's

    np_max-act · gemini-2.0-flash

    The neuron flags spans of direct quotation marks and the words inside them—that is, it detects quoted or spoken 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
    Tuy
    -0.07
    Х
    -0.07
     yönetimi
    -0.06
     arose
    -0.06
    Jur
    -0.06
    Depth
    -0.06
     Chang
    -0.06
    Quest
    -0.06
    فو
    -0.06
     jednodu
    -0.06
    POSITIVE LOGITS
    ussian
    0.07
     propositions
    0.06
    GB
    0.06
    Denied
    0.06
    ijke
    0.06
     Population
    0.06
     Morning
    0.06
    ности
    0.06
     trăm
    0.06
     blackjack
    0.06
    Activations Density 0.063%

    No Known Activations