© 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 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. 7-RESID-POST-AA
    11. 47983
    Prev
    Next
    INDEX
    Explanations

    Avoiding scams

    np_max-act · gemini-2.0-flash

    sentences or phrases warning users not to share credentials or personal/login information (e.g., "we will never ask" / requests for passwords, account details, or other sensitive data).

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    濟
    -0.06
     pers
    -0.06
     clips
    -0.06
    들
    -0.06
    adla
    -0.06
     NOTES
    -0.06
     showcasing
    -0.06
    prep
    -0.06
    	Player
    -0.06
     economies
    -0.06
    POSITIVE LOGITS
    complexContent
    0.06
    ứng
    0.06
    بد
    0.06
    Appear
    0.06
    osph
    0.06
    .Icon
    0.06
     活
    0.06
     màn
    0.06
    .mixin
    0.06
     craz
    0.06
    Activations Density 0.202%

    No Known Activations