© 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. 27837
    Prev
    Next
    INDEX
    Explanations

    when

    np_max-act · gemini-2.0-flash

    spots multiple-choice question formatting, especially answer-option labels and choice/answer fields.

    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_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
    uminium
    -0.07
     місті
    -0.06
    appId
    -0.06
    ())->
    -0.06
     Λα
    -0.06
     ]);
    -0.06
     bureaucratic
    -0.06
     facade
    -0.06
    亮
    -0.06
    .repo
    -0.06
    POSITIVE LOGITS
    ns
    0.09
     prudent
    0.08
     wed
    0.07
     harbor
    0.07
     Browser
    0.07
     giorno
    0.06
     shred
    0.06
    ообраз
    0.06
     carrot
    0.06
    finalize
    0.06
    Activations Density 0.518%

    No Known Activations