© 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. 15-RESID-POST-AA
    11. 128908
    Prev
    Next
    INDEX
    Explanations

    hypothetical questions

    np_max-act · gemini-2.0-flash

    sentences that begin hypothetical questions, especially "if you could/if you can (only) ..." constructions (conditional/hypothetical question openings).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cn
    -0.07
    ать
    -0.06
    ження
    -0.06
     tình
    -0.06
     Cadillac
    -0.06
     FC
    -0.06
    「お
    -0.06
    annah
    -0.06
     gays
    -0.06
    렇
    -0.06
    POSITIVE LOGITS
     SMA
    0.07
     comply
    0.07
     scrape
    0.06
     voucher
    0.06
     orders
    0.06
     Item
    0.06
     scri
    0.06
    妻
    0.06
    .State
    0.06
    sono
    0.06
    Activations Density 0.021%

    No Known Activations