© 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. 7-RESID-POST-AA
    11. 22503
    Prev
    Next
    INDEX
    Explanations

    Advice and recommendations

    np_max-act · gemini-2.0-flash

    Sentences or phrases that express advice, recommendations, warnings, or emphasis on importance/obligation (e.g., "it is important", "consult", "seek advice", "advisable").

    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
    .Utc
    -0.07
     lesser
    -0.07
    �
    -0.06
    orf
    -0.06
    debian
    -0.06
     tasty
    -0.06
    (ep
    -0.06
    .decode
    -0.06
    ontology
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    CTION
    0.06
     recognizer
    0.06
     LV
    0.06
    是不
    0.06
     Cooling
    0.06
     문의
    0.06
     Produ
    0.06
    Trigger
    0.06
     ни
    0.06
    ความร
    0.06
    Activations Density 0.135%

    No Known Activations