© 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. 15-RESID-POST-AA
    11. 27240
    Prev
    Next
    INDEX
    Explanations

    examples

    np_max-act · gemini-2.0-flash

    words and short phrases that introduce examples, explanations, or discourse transitions (e.g., "for example", "instance", "thus", "so").

    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
     bubbles
    -0.08
    	typedef
    -0.07
     "','
    -0.07
    capital
    -0.06
     laughter
    -0.06
     пло
    -0.06
    Mgr
    -0.06
    лки
    -0.06
     GetString
    -0.06
    filters
    -0.06
    POSITIVE LOGITS
    (P
    0.07
     sóc
    0.07
     thoát
    0.06
     centro
    0.06
    altimore
    0.06
     lành
    0.06
     �
    0.06
     suo
    0.06
    gregate
    0.06
    (prob
    0.05
    Activations Density 0.045%

    No Known Activations